From 00d0064362b75cab9da58433c616e8dc6de15d01 Mon Sep 17 00:00:00 2001 From: Miguel Jacq Date: Sat, 20 Jun 2026 18:27:22 +1000 Subject: [PATCH 01/25] Fixes for newlines in yaml --- src/jinjaturtle/erb.py | 2 +- src/jinjaturtle/handlers/yaml.py | 4 ++-- src/jinjaturtle/j2.py | 19 ++++++++++++++++--- tests/test_yaml_handler.py | 7 ++++++- 4 files changed, 25 insertions(+), 7 deletions(-) diff --git a/src/jinjaturtle/erb.py b/src/jinjaturtle/erb.py index 2c5788e..445ec51 100644 --- a/src/jinjaturtle/erb.py +++ b/src/jinjaturtle/erb.py @@ -157,7 +157,7 @@ class ErbTranslator: return self.ruby_value(expr) def statement_to_erb(self, stmt: str) -> str: - if stmt.endswith("-"): + if stmt.endswith(("-", "+")): stmt = stmt[:-1].rstrip() if stmt.startswith("for "): diff --git a/src/jinjaturtle/handlers/yaml.py b/src/jinjaturtle/handlers/yaml.py index 19013f8..1ad9bf3 100644 --- a/src/jinjaturtle/handlers/yaml.py +++ b/src/jinjaturtle/handlers/yaml.py @@ -510,10 +510,10 @@ class YamlHandler(DictLikeHandler): # into the rendered YAML and nesting the next top-level key. lines.append(f"{j2.for_start(item_var, collection_var)}{item_lines[0]}") lines.extend(item_lines[1:]) - lines.append(j2.for_end()) + lines.append(j2.for_end(keep_trailing_newline=True)) else: lines.append(j2.for_start(item_var, collection_var)) - lines.append(j2.for_end()) + lines.append(j2.for_end(keep_trailing_newline=True)) return "\n".join(lines) diff --git a/src/jinjaturtle/j2.py b/src/jinjaturtle/j2.py index 498a39e..13531f5 100644 --- a/src/jinjaturtle/j2.py +++ b/src/jinjaturtle/j2.py @@ -43,10 +43,19 @@ def to_json( return filtered(value, f"to_json({', '.join(args)})") -def statement(value: str, *, trim_right: bool = False) -> str: +def statement( + value: str, + *, + trim_right: bool = False, + keep_trailing_newline: bool = False, +) -> str: """Return a Jinja2 statement tag for an already-built statement body.""" + if trim_right and keep_trailing_newline: + raise ValueError("trim_right and keep_trailing_newline are mutually exclusive") if trim_right: return f"{{% {value} -%}}" + if keep_trailing_newline: + return f"{{% {value} +%}}" return f"{{% {value} %}}" @@ -66,8 +75,12 @@ def for_start(item_var: str, collection_var: str) -> str: return statement(f"for {item_var} in {collection_var}") -def for_end(*, trim_right: bool = False) -> str: - return statement("endfor", trim_right=trim_right) +def for_end(*, trim_right: bool = False, keep_trailing_newline: bool = False) -> str: + return statement( + "endfor", + trim_right=trim_right, + keep_trailing_newline=keep_trailing_newline, + ) def yaml_scalar_expression(var_name: str, raw_value: str | None = None) -> str: diff --git a/tests/test_yaml_handler.py b/tests/test_yaml_handler.py index 5c70e27..a217e8a 100644 --- a/tests/test_yaml_handler.py +++ b/tests/test_yaml_handler.py @@ -217,7 +217,7 @@ def test_yaml_loop_preserves_blank_separator_after_list(tmp_path: Path): def test_yaml_loop_preserves_following_top_level_comments(tmp_path: Path): - from jinja2 import Template + from jinja2 import Environment, Template from jinjaturtle.core import analyze_loops @@ -248,10 +248,15 @@ def test_yaml_loop_preserves_following_top_level_comments(tmp_path: Path): fmt, parsed, "role", original_text=text, loop_candidates=loop_candidates ) rendered = Template(template).render(**defaults) + ansible_rendered = ( + Environment(trim_blocks=True).from_string(template).render(**defaults) + ) assert "# Offense count: 2" in rendered assert "# This cop supports unsafe autocorrection" in rendered + assert "spec.rb\n\n# Offense count: 2" in ansible_rendered assert yaml.safe_load(rendered) == yaml.safe_load(text) + assert yaml.safe_load(ansible_rendered) == yaml.safe_load(text) def test_yaml_scalar_loop_preserves_quoted_list_items(tmp_path: Path): From 13d1a2b972b519fc4d44eb39c1170ee061ed9d14 Mon Sep 17 00:00:00 2001 From: Miguel Jacq Date: Sat, 20 Jun 2026 18:28:19 +1000 Subject: [PATCH 02/25] 0.5.5 --- debian/changelog | 6 ++++++ pyproject.toml | 2 +- rpm/jinjaturtle.spec | 4 +++- 3 files changed, 10 insertions(+), 2 deletions(-) diff --git a/debian/changelog b/debian/changelog index 44d4e28..1950637 100644 --- a/debian/changelog +++ b/debian/changelog @@ -1,3 +1,9 @@ +jinjaturtle (0.5.5) unstable; urgency=medium + + * erb support + + -- Miguel Jacq Sat, 20 Jun 2026 18:27:00 +1000 + jinjaturtle (0.5.4) unstable; urgency=medium * Make templates more faithful to the original file in terms of indentation, newlines, no deserialisation of things like < or >. diff --git a/pyproject.toml b/pyproject.toml index 1279f81..cbc30c8 100644 --- a/pyproject.toml +++ b/pyproject.toml @@ -1,6 +1,6 @@ [tool.poetry] name = "jinjaturtle" -version = "0.5.4" +version = "0.5.5" description = "Convert config files into Ansible defaults and Jinja2 templates." authors = ["Miguel Jacq "] license = "GPL-3.0-or-later" diff --git a/rpm/jinjaturtle.spec b/rpm/jinjaturtle.spec index a303b15..f354c18 100644 --- a/rpm/jinjaturtle.spec +++ b/rpm/jinjaturtle.spec @@ -1,4 +1,4 @@ -%global upstream_version 0.5.4 +%global upstream_version 0.5.5 Name: jinjaturtle Version: %{upstream_version} @@ -43,6 +43,8 @@ Convert config files into Ansible defaults and Jinja2 templates. %changelog * Sat Jun 20 2026 Miguel Jacq - %{version}-%{release} +- erb support +* Sat Jun 20 2026 Miguel Jacq - %{version}-%{release} - Make templates more faithful to the original file in terms of indentation, newlines, no deserialisation of things like < or >. - More test coverage * Fri Jun 19 2026 Miguel Jacq - %{version}-%{release} From f5de32b778503f6056069762211db685d1af34e6 Mon Sep 17 00:00:00 2001 From: Miguel Jacq Date: Sat, 20 Jun 2026 20:17:28 +1000 Subject: [PATCH 03/25] Rewrite the README --- README.md | 319 +++++++++++++++++++++++++++++++++++++++++++----------- 1 file changed, 257 insertions(+), 62 deletions(-) diff --git a/README.md b/README.md index 0e0ad48..26730fb 100644 --- a/README.md +++ b/README.md @@ -4,55 +4,230 @@ JinjaTurtle logo -JinjaTurtle is a command-line tool to help you generate Jinja2 templates and -Ansible inventory from a native configuration file (or files) of a piece of -software. +JinjaTurtle is a command-line tool that helps turn existing native +configuration files into reusable configuration-management templates. + +By default it generates: + +- a **Jinja2** template; and +- an **Ansible defaults YAML** file containing the variables used by that + template. + +It can also generate **ERB** templates and **Puppet Hiera-style YAML** data for +Puppet workflows. + +JinjaTurtle does not try to replace configuration-management tools. Its job is +to speed up the boring first pass: take a real config file, discover the values +inside it, replace those values with variables, and write the corresponding +variable data beside the template. ## How it works - * The config file(s) is/are examined - * Parameter key names are generated based on the parameter names in the - config file. In keeping with Ansible best practices, you pass a prefix - for the key names, which should typically match the name of your Ansible - role. - * A Jinja2 file is generated from the file with those parameter key names - injected as the `{{ variable }}` names. - * An Ansible inventory YAML file is generated with those key names and the - *values* taken from the original config file as the default vars. +JinjaTurtle examines a source config file and keeps the original structure as +much as possible. -By default, the Jinja2 template and the Ansible inventory are printed to -stdout. However, it is possible to output the results to new files. +For the default Jinja2/Ansible mode: + +1. The config file is parsed. +2. Variable names are generated from the config keys and paths. +3. Those variable names are prefixed with `--role-name`, which should usually + match your Ansible role name. +4. A Jinja2 template is generated with values replaced by `{{ variable }}` + expressions. +5. An Ansible defaults YAML file is generated with those variables and the + original values. + +For ERB/Puppet mode: + +1. The same parse/flatten/loop analysis is used. +2. An ERB template is generated with Puppet-style instance variables such as + `<%= @memory_limit %>`. +3. The variables file is written as Puppet Hiera-style data, such as + `php::memory_limit: 256M`. +4. If `--puppet-class` is supplied, that class name is used as the Hiera + namespace while `--role-name` remains the local variable prefix. + +By default, the generated variable data and template are printed to stdout. Use +`--defaults-output` and `--template-output` to write them to files. + +## Jinja2 / Ansible example + +Say you have a `php.ini` file and you are inside an Ansible role with +`defaults/` and `templates/` directories: + +```shell +jinjaturtle php.ini \ + --role-name php \ + --defaults-output defaults/main.yml \ + --template-output templates/php.ini.j2 +``` + +Given a source value such as: + +```ini +memory_limit = 256M +``` + +JinjaTurtle will produce a template value like: + +```jinja2 +memory_limit = {{ php_memory_limit }} +``` + +and defaults data like: + +```yaml +php_memory_limit: 256M +``` + +## ERB / Puppet example + +Use `--template-engine erb` when you want Puppet ERB output: + +```shell +jinjaturtle php.ini \ + --role-name php \ + --template-engine erb \ + --defaults-output data/common.yaml \ + --template-output templates/php.ini.erb +``` + +Given the same source value: + +```ini +memory_limit = 256M +``` + +JinjaTurtle will produce an ERB template value like: + +```erb +memory_limit = <%= @memory_limit %> +``` + +and Hiera-style data like: + +```yaml +php::memory_limit: 256M +``` + +The `--defaults-output` option name is retained for CLI compatibility, but in +ERB mode the file is intended to be Puppet Hiera data rather than Ansible role +defaults. + +JinjaTurtle does **not** generate Puppet classes or `file` resources. A Puppet +module, or another tool such as Enroll, should still declare the class +parameters and call the template, for example with Puppet's `template()` +function. + +## Using `--puppet-class` + +Most direct usage can simply use the same value for the role name and Puppet +class name: + +```shell +jinjaturtle php.ini --role-name php --template-engine erb +``` + +This creates Hiera keys such as: + +```yaml +php::memory_limit: 256M +``` + +and local ERB variables such as: + +```erb +<%= @memory_limit %> +``` + +For generated systems, it can be useful to make `--role-name` more specific +while keeping the Hiera keys under the real Puppet class. For example: + +```shell +jinjaturtle php.ini \ + --role-name php_etc_php_ini \ + --puppet-class php \ + --template-engine erb +``` + +In that case the variable prefix can stay file-specific, while the Hiera data +is still written under `php::...`. ## What sort of config files can it handle? -TOML, YAML, INI, JSON and XML-style config files should be okay. There are always -going to be some edge cases in very complex files that are difficult to work -with, though, so you may still find that you need to tweak the results. +JinjaTurtle supports common structured and semi-structured config formats: -For XML and YAML files, JinjaTurtle will attempt to generate 'for' loops -and lists in the Ansible yaml if the config file looks homogenous enough to -support it. However, if it lacks the confidence in this, it will fall back to -using scalar-style flattened attributes. +- TOML +- YAML +- INI-style files +- JSON +- XML +- Postfix `main.cf` +- systemd unit files, such as `*.service`, `*.socket`, `*.timer`, and related + unit types +- OpenSSH-style config files, including `ssh_config`, `sshd_config`, and common + `*.conf` snippets detected as SSH config -You may need or wish to tidy up the config to suit your needs. +For ambiguous extensions such as `*.conf`, JinjaTurtle uses lightweight content +sniffing. You can always force a handler with `--format`. -The goal here is really to *speed up* converting files into Ansible/Jinja2, -but not necessarily to make it perfect. +For YAML, XML, TOML, INI-style, and other supported structured files, +JinjaTurtle will attempt to generate loops when a repeated structure looks +homogeneous enough. If it is not confident, it falls back to flattened scalar +variables. + +Some very complex files will still need manual cleanup. The goal is to speed up +conversion into Jinja2 or ERB templates, not to guarantee a perfect final module +without review. + +## JSON, quoting, and type preservation + +JinjaTurtle tries to preserve rendered config types. + +For JSON, it uses JSON-aware expressions rather than plain string substitution. +This avoids generating invalid JSON such as: + +```json +{"enabled": True} +``` + +when the correct rendered JSON should be: + +```json +{"enabled": true} +``` + +In Jinja2 mode this uses Ansible-style JSON filters. In ERB mode it emits Ruby +JSON generation where required, for example: + +```erb +<% require 'json' -%> +{ + "enabled": <%= JSON.generate(@enabled) %> +} +``` + +That is expected for JSON ERB templates. ## Can I convert multiple files at once? -Certainly! Pass the folder name instead of a specific file name, and JinjaTurtle -will convert any files it understands in that folder, storing all the various -vars in the destination defaults yaml file, and converting each file into a -Jinja2 template per file type. +Yes. Pass a directory instead of a single file and JinjaTurtle will convert the +files it understands in that directory. -If all the files had the same 'type', there'll be one Jinja2 template. +```shell +jinjaturtle ./config-dir \ + --role-name myrole \ + --defaults-output defaults/main.yml \ + --template-output templates/ +``` -You can also pass `--recursive` to recurse into subfolders. +Use `--recursive` to recurse into subdirectories. -Note: when using 'folder' mode and multiple files of the same type, their vars -will be listed under an 'items' parent key in the yaml, each with an `id` key. -You'll then want to use a `loop` in Ansible later, e.g: +In folder mode, variables for multiple files of the same type are grouped under +an `items`-style structure in the generated YAML so that the resulting templates +can be used with loops in Ansible. + +For example: ```yaml - name: Render configs @@ -93,9 +268,9 @@ sudo dnf upgrade --refresh sudo dnf install jinjaturtle ``` -### From PyPi +### From PyPI -``` +```bash pip install jinjaturtle ``` @@ -103,61 +278,81 @@ pip install jinjaturtle Clone the repo and then run inside the clone: -``` +```bash poetry install ``` ### AppImage -Download the AppImage from the Releases and make it executable, and put it -on your `$PATH`. - -## How to run it - -Say you have a `php.ini` file and you are in a directory structure like an -Ansible role (with subfolders `defaults` and `templates`): - -```shell -jinjaturtle php.ini \ - --role-name php \ - --defaults-output defaults/main.yml \ - --template-output templates/php.ini.j2 -``` +Download the AppImage from the Releases page, make it executable, and put it on +your `$PATH`. ## Full usage info -``` -usage: jinjaturtle [-h] -r ROLE_NAME [-f {json,ini,toml,yaml,xml,postfix,systemd}] [-d DEFAULTS_OUTPUT] [-t TEMPLATE_OUTPUT] config +```text +usage: jinjaturtle [-h] [-r ROLE_NAME] [--recursive] + [-f {ini,json,toml,yaml,xml,postfix,systemd,ssh}] + [-d DEFAULTS_OUTPUT] [-t TEMPLATE_OUTPUT] + [--template-engine {jinja2,erb}] + [--puppet-class PUPPET_CLASS] + config -Convert a config file into Ansible inventory and a Jinja2 template. +Convert a config file into an Ansible defaults file and Jinja2 template. positional arguments: - config Path to the source configuration file. + config Path to a config file OR a folder containing supported + config files. Supported: .toml, .yaml/.yml, .json, + .ini/.cfg/.conf, .xml, ssh_config/sshd_config options: -h, --help show this help message and exit -r, --role-name ROLE_NAME - Ansible role name, used as variable prefix (e.g. cometbft). - -f, --format {ini,json,toml,xml} - Force config format instead of auto-detecting from filename. + Role name / variable prefix. In Jinja2 mode this is + usually the Ansible role name. In ERB mode it is used + as the local variable prefix. Defaults to jinjaturtle. + --recursive When CONFIG is a folder, recurse into subfolders. + -f, --format {ini,json,toml,yaml,xml,postfix,systemd,ssh} + Force config format instead of auto-detecting from + filename. -d, --defaults-output DEFAULTS_OUTPUT - Path to write defaults/main.yml. If omitted, default vars are printed to stdout. + Path to write the generated variable YAML. If omitted, + it is printed to stdout. -t, --template-output TEMPLATE_OUTPUT - Path to write the Jinja2 config template. If omitted, template is printed to stdout. + Path to write the generated config template. If omitted, + it is printed to stdout. + --template-engine {jinja2,erb} + Template syntax to generate. Defaults to jinja2. Use + erb for Puppet templates. + --puppet-class PUPPET_CLASS + Puppet class / Hiera namespace to use with + --template-engine erb. Defaults to --role-name. ``` ## Additional supported formats -JinjaTurtle can also template some common "bespoke" config formats: +JinjaTurtle also templates some common bespoke config formats: - **Postfix main.cf** (`main.cf`) → `--format postfix` - **systemd unit files** (`*.service`, `*.socket`, etc.) → `--format systemd` +- **OpenSSH config** (`ssh_config`, `sshd_config`, and detected snippets) → + `--format ssh` -For ambiguous extensions like `*.conf`, JinjaTurtle uses lightweight content sniffing; you can always force a specific handler via `--format`. +For ambiguous extensions like `*.conf`, JinjaTurtle uses lightweight content +sniffing. You can always force a specific handler with `--format`. +## Relationship with Enroll + +JinjaTurtle can be used directly, but it is also useful as a helper for tools +that generate configuration-management code. + +Enroll can call JinjaTurtle when it is available on the `PATH`. In that setup, +Enroll decides where Puppet, Ansible, or Salt files belong, while JinjaTurtle +concentrates on converting harvested config files into templates plus variable +data. ## Found a bug, have a suggestion? -You can e-mail me (see the pyproject.toml for details) or contact me on the Fediverse: +You can e-mail me; see `pyproject.toml` for details. You can also contact me on +the Fediverse: https://goto.mig5.net/@mig5 From a5ca5f29742c54205b6eb64eb6efe280a3cf2fc4 Mon Sep 17 00:00:00 2001 From: Miguel Jacq Date: Tue, 23 Jun 2026 14:20:00 +1000 Subject: [PATCH 04/25] Try to prevent what could lead to execution of embedded jinja in original files when converting --- README.md | 57 ++++++-- src/jinjaturtle/cli.py | 6 +- src/jinjaturtle/core.py | 2 - src/jinjaturtle/erb.py | 41 ++++-- src/jinjaturtle/escape.py | 148 +++++++++++++++++++ src/jinjaturtle/handlers/ini.py | 26 +++- src/jinjaturtle/handlers/postfix.py | 22 +-- src/jinjaturtle/handlers/ssh.py | 12 +- src/jinjaturtle/handlers/systemd.py | 19 ++- src/jinjaturtle/handlers/toml.py | 106 +++++++++----- src/jinjaturtle/handlers/xml.py | 45 +++++- src/jinjaturtle/handlers/yaml.py | 45 +++--- tests/test_injection_security.py | 212 ++++++++++++++++++++++++++++ 13 files changed, 640 insertions(+), 101 deletions(-) create mode 100644 src/jinjaturtle/escape.py create mode 100644 tests/test_injection_security.py diff --git a/README.md b/README.md index 26730fb..8423cb7 100644 --- a/README.md +++ b/README.md @@ -115,9 +115,8 @@ ERB mode the file is intended to be Puppet Hiera data rather than Ansible role defaults. JinjaTurtle does **not** generate Puppet classes or `file` resources. A Puppet -module, or another tool such as Enroll, should still declare the class -parameters and call the template, for example with Puppet's `template()` -function. +module, should still declare the class parameters and call the template, for +example with Puppet's `template()` function. ## Using `--puppet-class` @@ -340,15 +339,53 @@ JinjaTurtle also templates some common bespoke config formats: For ambiguous extensions like `*.conf`, JinjaTurtle uses lightweight content sniffing. You can always force a specific handler with `--format`. -## Relationship with Enroll +## Security model -JinjaTurtle can be used directly, but it is also useful as a helper for tools -that generate configuration-management code. +JinjaTurtle is frequently pointed at config files that were *harvested* from +real systems, where some content may be influenced by an untrusted party (a +hostname, a login banner, a `GECOS` comment, a "Managed by ..." note). It is +therefore designed so that source content cannot turn into executable template +code. + +Two guarantees matter: + +1. **Values are data, never code.** Every config *value* is replaced with a + `{{ variable }}` placeholder in the template, and the original value is stored + separately in the defaults/Hiera data. When the template is later rendered, + the placeholder prints the value as a literal string; Jinja2 does not + recursively render the *contents* of a variable, so a payload sitting inside + a value (for example `motd = {{ salt['cmd.run']('id') }}`) is inert. + +2. **Verbatim text is neutralised.** To preserve formatting, JinjaTurtle copies + comments, blank lines, headers and any unrecognised lines from the source + into the template. Any template metacharacters in that copied text + (`{{ }}`, `{% %}`, `{# #}` for Jinja2; `<% %>` for ERB) are escaped so they + render as the literal characters the author wrote, rather than executing. + +### Consumer responsibilities + +The value guarantee above relies on the downstream renderer being single-pass, +which is the normal case: + +- **Ansible**: rendering a template with `template:`/`ansible.builtin.template` + is single-pass. For defence in depth, treat the generated defaults as + untrusted input — Ansible already does not re-template variable *contents* by + default. If you build your own var structures from this data and pass them + through additional templating, mark untrusted values with the `!unsafe` tag so + they are never re-evaluated. +- **Salt**: use the generated file as a `file.managed` template + (`template: jinja`). Do **not** place JinjaTurtle output where Salt would + render it a second time as part of SLS/pillar rendering, which is a separate + Jinja pass and would re-evaluate any embedded expressions. +- **Puppet/ERB**: render with the standard `template()`/`epp()` flow. + +In short: render JinjaTurtle output exactly once. Do not feed it back through +another templating pass. + +**IMPORTANT**: Always review both the original config files, then the resulting +templates generated by JinjaTurtle, before integrating them into your config +management system! -Enroll can call JinjaTurtle when it is available on the `PATH`. In that setup, -Enroll decides where Puppet, Ansible, or Salt files belong, while JinjaTurtle -concentrates on converting harvested config files into templates plus variable -data. ## Found a bug, have a suggestion? diff --git a/src/jinjaturtle/cli.py b/src/jinjaturtle/cli.py index 7658bfb..0c403fa 100644 --- a/src/jinjaturtle/cli.py +++ b/src/jinjaturtle/cli.py @@ -199,4 +199,8 @@ def main() -> None: """ Console-script entry point. """ - _main(sys.argv[1:]) + sys.exit(_main(sys.argv[1:])) + + +if __name__ == "__main__": + main() diff --git a/src/jinjaturtle/core.py b/src/jinjaturtle/core.py index 673aad0..1faefca 100644 --- a/src/jinjaturtle/core.py +++ b/src/jinjaturtle/core.py @@ -412,8 +412,6 @@ def generate_puppet_hiera_yaml( ``role_prefix`` remains the source variable prefix used by JinjaTurtle while ``puppet_class`` is the Puppet class/Hiera namespace. In the normal case they are the same, so ``php_memory_limit`` becomes ``php::memory_limit``. - Enroll may pass a file-specific role prefix and a separate Puppet class to - avoid parameter-name collisions inside one generated Puppet module. """ klass = puppet_class_name(puppet_class or role_prefix) diff --git a/src/jinjaturtle/erb.py b/src/jinjaturtle/erb.py index 445ec51..6eb26ad 100644 --- a/src/jinjaturtle/erb.py +++ b/src/jinjaturtle/erb.py @@ -2,6 +2,8 @@ from __future__ import annotations import re +from .escape import escape_erb_literal + def _safe_name(raw: str, *, fallback: str = "var") -> str: text = re.sub(r"[^A-Za-z0-9_]+", "_", str(raw or fallback)).strip("_").lower() @@ -38,10 +40,9 @@ def puppet_local_var_name( generated Jinja variable such as ``php_memory_limit`` becomes Puppet local parameter ``memory_limit`` and Hiera key ``php::memory_limit``. - Enroll sometimes needs a file-specific variable prefix to avoid collisions - inside a generated module. When ``puppet_class`` differs from - ``role_prefix`` we keep the full generated variable name as the local - parameter and only use ``puppet_class`` as the Hiera namespace. + When ``puppet_class`` differs from ``role_prefix`` we keep the full + generated variable name as the local parameter and only use ``puppet_class`` + as the Hiera namespace. """ var_name = _safe_name(jinja_var_name, fallback="value") @@ -71,7 +72,33 @@ class ErbTranslator: self.loop_stack: list[tuple[str, str, str]] = [] self.needs_json = False + # Matches a JinjaTurtle ``{% raw %} ... {% endraw %}`` block (non-greedy). + # JinjaTurtle emits raw blocks only to carry verbatim, security-escaped + # source text (comments and unrecognised lines), so the *contents* must be + # treated as literal output, never translated as Jinja tokens. + _RAW_BLOCK_RE = re.compile(r"{%\s*raw\s*%}(.*?){%\s*endraw\s*%}", re.S) + def translate(self, template_text: str) -> str: + # Split out raw blocks first. Their inner text is literal and must be + # carried through as literal ERB (with ERB delimiters re-escaped), rather + # than tokenised -- otherwise an escaped Jinja payload inside a comment + # would be "re-animated" into live ERB during translation. + segments = self._RAW_BLOCK_RE.split(template_text) + out: list[str] = [] + # re.split with one capture group yields: [text, raw_inner, text, ...]. + for idx, segment in enumerate(segments): + if idx % 2 == 1: + # Captured raw-block contents: emit as literal ERB text. + out.append(escape_erb_literal(segment)) + else: + out.append(self._translate_tokens(segment)) + + rendered = "".join(out) + if self.needs_json and "require 'json'" not in rendered: + rendered = "<% require 'json' -%>\n" + rendered + return rendered + + def _translate_tokens(self, template_text: str) -> str: parts = self._TOKEN_RE.split(template_text) out: list[str] = [] for token in parts: @@ -86,11 +113,7 @@ class ErbTranslator: out.append(self.statement_to_erb(stmt)) continue out.append(token) - - rendered = "".join(out) - if self.needs_json and "require 'json'" not in rendered: - rendered = "<% require 'json' -%>\n" + rendered - return rendered + return "".join(out) def local_var(self, name: str) -> str: return puppet_local_var_name( diff --git a/src/jinjaturtle/escape.py b/src/jinjaturtle/escape.py new file mode 100644 index 0000000..3b8575e --- /dev/null +++ b/src/jinjaturtle/escape.py @@ -0,0 +1,148 @@ +from __future__ import annotations + +"""Neutralise template metacharacters in text copied verbatim from source files. + +JinjaTurtle preserves formatting by copying parts of the *original* config file +straight into the generated template: comments, blank lines, section headers, +and any line it does not recognise as ``key = value``. Config *values* are +always replaced with ``{{ var }}`` placeholders and parked in the defaults data, +so a payload inside a value is inert. Verbatim text is different: if the source +contains ``{{ ... }}``, ``{% ... %}`` or ``{# ... #}`` (Jinja2), or ``<%= %>`` / +``<% %>`` (ERB), that text becomes *live template code* in the output and is +executed when Salt/Ansible/Puppet later renders the template. + +Because JinjaTurtle is frequently fed harvested, attacker-influenceable config +(hostnames, banners, GECOS-derived comments, "Managed by" notes), this is a +template-injection / SSTI vector that can lead to remote code execution on the +configuration-management control node. + +The functions here render those metacharacters as literal text so they survive a +later template render as the characters the source author actually wrote, rather +than as executable template syntax. + +Design notes: + * We only ever escape text that originates from the *source file*. We never + pass JinjaTurtle's own generated placeholders (``{{ role_var }}``) through + these helpers, so the placeholders keep working. + * Jinja2 literal text is wrapped in a single ``{% raw %} ... {% endraw %}`` + block. ``raw`` disables *all* tag interpretation inside it -- expressions, + statements and ``{# #}`` comments alike -- so one wrap neutralises every + Jinja construct. The only way to break out of a raw block is a literal + ``{% endraw %}`` in the source, so we defang the token ``endraw`` (in any + internal spacing) before wrapping. + * The ERB translator (``erb.py``) is raw-aware: it copies the *contents* of a + JinjaTurtle raw block through as literal ERB text and re-escapes any ERB + delimiters found there. That keeps a Jinja-escaped comment inert after the + Jinja2 -> ERB translation step, instead of the payload being "re-animated" + as ERB. + * ``escape_erb_literal`` exists for completeness / direct ERB emission: it + rewrites each ERB delimiter into an ERB expression that prints the delimiter + characters literally. +""" + +import re + +# Jinja2 delimiters we must neutralise. Engine-default; JinjaTurtle never +# configures custom delimiters. +_JINJA_MARKERS = ("{{", "}}", "{%", "%}", "{#", "#}") + +# ERB delimiters. Longer markers first so "<%=" matches before "<%". +_ERB_OPEN_MARKERS = ("<%=", "<%-", "<%#", "<%") +_ERB_CLOSE_MARKERS = ("-%>", "%>") + +# Matches a Jinja2 endraw tag in any internal spacing, e.g. "{%endraw%}", +# "{% endraw %}", "{%- endraw -%}". +_ENDRAW_RE = re.compile(r"{%-?\s*endraw\s*-?%}") + +# Sentinel inserted between "end" and "raw" to break the endraw keyword without +# changing the visible characters. We use a Jinja comment-free approach: insert +# the two halves across a raw boundary so the literal text still reads "endraw" +# to a human but is never a valid tag. See escape_jinja_literal for usage. + + +def contains_jinja_markup(text: str) -> bool: + """Return True if *text* contains any Jinja2 delimiter.""" + return any(m in text for m in _JINJA_MARKERS) + + +def contains_erb_markup(text: str) -> bool: + """Return True if *text* contains any ERB delimiter.""" + return any(m in text for m in (*_ERB_OPEN_MARKERS, *_ERB_CLOSE_MARKERS)) + + +def _defang_endraw(text: str) -> str: + """Rewrite any literal ``{% endraw %}`` so it cannot close our raw wrapper. + + We turn each endraw tag into ``{% endraw %}{{ '{% endraw %}' }}{% raw %}``... + no -- that would re-introduce live tags. Instead we keep everything literal: + we break the keyword by emitting the tag's text in two raw segments split + inside the word ``endraw``. The result, when later rendered, reproduces the + exact original characters ``{% endraw %}`` while never being a parseable tag. + """ + + def _replace(match: re.Match[str]) -> str: + tag = match.group(0) + # Split the keyword "endraw" as "end" + "raw"; close and reopen the raw + # block between them. Each half is plain text inside a raw block, so the + # reconstructed output is byte-identical to the original tag, but at no + # point does the token "{% endraw %}" exist contiguously to close raw. + idx = tag.lower().index("endraw") + head = tag[: idx + 3] # up to and including "end" + tail = tag[idx + 3 :] # "raw...%}" + return f"{head}{{% endraw %}}{{% raw %}}{tail}" + + return _ENDRAW_RE.sub(_replace, text) + + +def escape_jinja_literal(text: str) -> str: + """Make *text* render as literal characters under a later Jinja2 render. + + Text with no Jinja metacharacters is returned unchanged so the common case + stays byte-for-byte identical to the source. Otherwise the text is wrapped + in a single ``{% raw %}`` block, with any embedded ``endraw`` defanged. + """ + if not text or not contains_jinja_markup(text): + return text + return "{% raw %}" + _defang_endraw(text) + "{% endraw %}" + + +def escape_erb_literal(text: str) -> str: + """Make *text* render as literal characters under a later ERB render. + + ERB has no ``raw`` block, so each opening/closing delimiter is rewritten as + an ERB expression that prints the delimiter literally. Text with no ERB + metacharacters is returned unchanged. + """ + if not text or not contains_erb_markup(text): + return text + + result: list[str] = [] + i = 0 + n = len(text) + while i < n: + matched = None + for marker in (*_ERB_CLOSE_MARKERS, *_ERB_OPEN_MARKERS): + if text.startswith(marker, i): + matched = marker + break + if matched is not None: + escaped = matched.replace("\\", "\\\\").replace('"', '\\"') + result.append('<%= "' + escaped + '" %>') + i += len(matched) + else: + result.append(text[i]) + i += 1 + return "".join(result) + + +def escape_literal(text: str, *, engine: str = "jinja2") -> str: + """Escape verbatim *text* for the target template *engine*. + + ``engine`` is ``"jinja2"`` (default) or ``"erb"``. Unknown engines fall back + to Jinja2 escaping. In JinjaTurtle's pipeline ERB output is produced by + translating Jinja2 output, and the translator is raw-aware, so handlers can + always Jinja-escape and rely on the translator to keep the literal inert. + """ + if engine == "erb": + return escape_erb_literal(text) + return escape_jinja_literal(text) diff --git a/src/jinjaturtle/handlers/ini.py b/src/jinjaturtle/handlers/ini.py index 1aa5e22..9f50839 100644 --- a/src/jinjaturtle/handlers/ini.py +++ b/src/jinjaturtle/handlers/ini.py @@ -6,6 +6,7 @@ from typing import Any from . import BaseHandler from .. import j2 +from ..escape import escape_jinja_literal class IniHandler(BaseHandler): @@ -84,16 +85,18 @@ class IniHandler(BaseHandler): line = raw_line stripped = line.lstrip() - # Blank or pure comment: keep as-is + # Blank or pure comment: keep formatting, but neutralise any + # template metacharacters so attacker-controlled comment text cannot + # become live template code in the output. if not stripped or stripped[0] in {"#", ";"}: - out_lines.append(raw_line) + out_lines.append(escape_jinja_literal(raw_line)) continue # Section header if stripped.startswith("[") and "]" in stripped: header_inner = stripped[1 : stripped.index("]")] current_section = header_inner.strip() - out_lines.append(raw_line) + out_lines.append(escape_jinja_literal(raw_line)) continue # Work without newline so we can re-attach it exactly @@ -108,8 +111,9 @@ class IniHandler(BaseHandler): eq_index = content.find("=") if eq_index == -1: - # Not a simple key=value line: leave untouched - out_lines.append(raw_line) + # Not a simple key=value line: leave content intact but escape + # any template metacharacters. + out_lines.append(escape_jinja_literal(raw_line)) continue before_eq = content[:eq_index] @@ -117,7 +121,7 @@ class IniHandler(BaseHandler): key = before_eq.strip() if not key: - out_lines.append(raw_line) + out_lines.append(escape_jinja_literal(raw_line)) continue # Whitespace after '=' @@ -146,8 +150,16 @@ class IniHandler(BaseHandler): else: replacement_value = j2.variable(var_name) + # ``before_eq`` (key + surrounding whitespace) and ``comment_part`` + # both originate from the source file and may carry template + # metacharacters; escape each independently so the safe + # ``replacement_value`` placeholder between them is preserved. new_content = ( - before_eq + "=" + leading_ws + replacement_value + comment_part + escape_jinja_literal(before_eq) + + "=" + + leading_ws + + replacement_value + + escape_jinja_literal(comment_part) ) out_lines.append(new_content + newline) diff --git a/src/jinjaturtle/handlers/postfix.py b/src/jinjaturtle/handlers/postfix.py index e2e442a..f6a1974 100644 --- a/src/jinjaturtle/handlers/postfix.py +++ b/src/jinjaturtle/handlers/postfix.py @@ -5,6 +5,7 @@ from typing import Any from . import BaseHandler from .. import j2 +from ..escape import escape_jinja_literal class PostfixMainHandler(BaseHandler): @@ -108,16 +109,16 @@ class PostfixMainHandler(BaseHandler): stripped = content.strip() if not stripped: - out_lines.append(raw_line) + out_lines.append(escape_jinja_literal(raw_line)) i += 1 continue if stripped.startswith("#"): - out_lines.append(raw_line) + out_lines.append(escape_jinja_literal(raw_line)) i += 1 continue if "=" not in content: - out_lines.append(raw_line) + out_lines.append(escape_jinja_literal(raw_line)) i += 1 continue @@ -127,7 +128,7 @@ class PostfixMainHandler(BaseHandler): key = before_eq.strip() if not key: - out_lines.append(raw_line) + out_lines.append(escape_jinja_literal(raw_line)) i += 1 continue @@ -162,16 +163,21 @@ class PostfixMainHandler(BaseHandler): var = self.make_var_name(role_prefix, (key,)) v = value + # ``before_eq`` (key) and ``comment_part`` are source-derived and may + # contain template metacharacters; escape each around the safe + # placeholder. + safe_before = escape_jinja_literal(before_eq) + safe_comment = escape_jinja_literal(comment_part) quoted = len(v) >= 2 and v[0] == v[-1] and v[0] in {'"', "'"} if quoted: replacement = ( - f"{before_eq}={leading_ws}{j2.quoted_variable(var)}" - f"{comment_part}{newline}" + f"{safe_before}={leading_ws}{j2.quoted_variable(var)}" + f"{safe_comment}{newline}" ) else: replacement = ( - f"{before_eq}={leading_ws}{j2.variable(var)}" - f"{comment_part}{newline}" + f"{safe_before}={leading_ws}{j2.variable(var)}" + f"{safe_comment}{newline}" ) out_lines.append(replacement) diff --git a/src/jinjaturtle/handlers/ssh.py b/src/jinjaturtle/handlers/ssh.py index a6c0d2f..f588a33 100644 --- a/src/jinjaturtle/handlers/ssh.py +++ b/src/jinjaturtle/handlers/ssh.py @@ -7,6 +7,7 @@ from typing import Any from . import BaseHandler from .. import j2 +from ..escape import escape_jinja_literal _SECTION_KEYWORDS = {"host", "match"} @@ -255,12 +256,12 @@ class SshConfigHandler(BaseHandler): out_lines: list[str] = [] for ln in parsed.lines: if ln.kind != "kv": - out_lines.append(ln.raw) + out_lines.append(escape_jinja_literal(ln.raw)) continue path = self._path_for_line(ln) if not path: - out_lines.append(ln.raw) + out_lines.append(escape_jinja_literal(ln.raw)) continue var = self.make_var_name(role_prefix, path) @@ -270,9 +271,12 @@ class SshConfigHandler(BaseHandler): else: replacement_value = j2.variable(var) + # ``before_value`` (keyword + spacing) and ``comment`` are + # source-derived; escape around the safe placeholder. rendered = ( - f"{ln.before_value}{replacement_value}" - f"{ln.whitespace_before_comment}{ln.comment}{ln.newline}" + f"{escape_jinja_literal(ln.before_value)}{replacement_value}" + f"{ln.whitespace_before_comment}" + f"{escape_jinja_literal(ln.comment)}{ln.newline}" ) out_lines.append(rendered) diff --git a/src/jinjaturtle/handlers/systemd.py b/src/jinjaturtle/handlers/systemd.py index 8118808..d28a8c5 100644 --- a/src/jinjaturtle/handlers/systemd.py +++ b/src/jinjaturtle/handlers/systemd.py @@ -6,6 +6,7 @@ from typing import Any from . import BaseHandler from .. import j2 +from ..escape import escape_jinja_literal @dataclass @@ -157,7 +158,13 @@ class SystemdUnitHandler(BaseHandler): out_lines: list[str] = [] for ln in parsed.lines: if ln.kind != "kv" or not ln.section or not ln.key: - out_lines.append(ln.raw) + # Verbatim lines (blank/comment/section/unrecognised "raw") + # originate from the source file. Escape template + # metacharacters so they cannot become live template code. + # This is the only handler that emits unrecognised lines, which + # is where Jinja *statement* injection (``{% ... %}``) was + # possible, so escaping here is essential. + out_lines.append(escape_jinja_literal(ln.raw)) continue path: tuple[str, ...] = (ln.section, ln.key) @@ -166,16 +173,18 @@ class SystemdUnitHandler(BaseHandler): var = self.make_var_name(role_prefix, path) v = (ln.value or "").strip() + safe_before = escape_jinja_literal(ln.before_eq) + safe_comment = escape_jinja_literal(ln.comment) quoted = len(v) >= 2 and v[0] == v[-1] and v[0] in {'"', "'"} if quoted: repl = ( - f"{ln.before_eq}={ln.leading_ws_after_eq}" - f"{j2.quoted_variable(var)}{ln.comment}" + f"{safe_before}={ln.leading_ws_after_eq}" + f"{j2.quoted_variable(var)}{safe_comment}" ) else: repl = ( - f"{ln.before_eq}={ln.leading_ws_after_eq}" - f"{j2.variable(var)}{ln.comment}" + f"{safe_before}={ln.leading_ws_after_eq}" + f"{j2.variable(var)}{safe_comment}" ) newline = "\n" if ln.raw.endswith("\n") else "" diff --git a/src/jinjaturtle/handlers/toml.py b/src/jinjaturtle/handlers/toml.py index 15d5a2a..6d25cff 100644 --- a/src/jinjaturtle/handlers/toml.py +++ b/src/jinjaturtle/handlers/toml.py @@ -5,6 +5,7 @@ from typing import Any from . import DictLikeHandler from .. import j2 +from ..escape import escape_jinja_literal from ..loop_analyzer import LoopCandidate try: @@ -77,19 +78,25 @@ class TomlHandler(DictLikeHandler): def emit_kv(path: tuple[str, ...], key: str, value: Any) -> None: var_name = self.make_var_name(role_prefix, path + (key,)) if isinstance(value, str): - lines.append(f"{key} = {self._toml_quoted_expr(var_name)}") + lines.append( + f"{escape_jinja_literal(str(key))} = {self._toml_quoted_expr(var_name)}" + ) elif isinstance(value, bool): # Booleans need | lower filter (Python True/False → TOML true/false) - lines.append(f"{key} = {self._toml_value_expr(var_name, value)}") + lines.append( + f"{escape_jinja_literal(str(key))} = {self._toml_value_expr(var_name, value)}" + ) else: - lines.append(f"{key} = {self._toml_value_expr(var_name, value)}") + lines.append( + f"{escape_jinja_literal(str(key))} = {self._toml_value_expr(var_name, value)}" + ) def walk(obj: dict[str, Any], path: tuple[str, ...] = ()) -> None: scalar_items = {k: v for k, v in obj.items() if not isinstance(v, dict)} nested_items = {k: v for k, v in obj.items() if isinstance(v, dict)} if path: - header = ".".join(path) + header = ".".join(escape_jinja_literal(str(p)) for p in path) lines.append(f"[{header}]") for key, val in scalar_items.items(): @@ -130,10 +137,14 @@ class TomlHandler(DictLikeHandler): def emit_kv(path: tuple[str, ...], key: str, value: Any) -> None: var_name = self.make_var_name(role_prefix, path + (key,)) if isinstance(value, str): - lines.append(f"{key} = {self._toml_quoted_expr(var_name)}") + lines.append( + f"{escape_jinja_literal(str(key))} = {self._toml_quoted_expr(var_name)}" + ) elif isinstance(value, bool): # Booleans need | lower filter (Python True/False → TOML true/false) - lines.append(f"{key} = {self._toml_value_expr(var_name, value)}") + lines.append( + f"{escape_jinja_literal(str(key))} = {self._toml_value_expr(var_name, value)}" + ) elif isinstance(value, list): # Check if this list is a loop candidate if path + (key,) in loop_paths: @@ -157,19 +168,26 @@ class TomlHandler(DictLikeHandler): elif candidate.item_schema in ("simple_dict", "nested"): # Dict list loop - TOML array of tables # This is complex for TOML, using simplified approach - lines.append(f"{key} = " f"{j2.to_json(var_name)}") + lines.append( + f"{escape_jinja_literal(str(key))} = " + f"{j2.to_json(var_name)}" + ) else: # Not a loop, treat as regular variable - lines.append(f"{key} = {self._toml_value_expr(var_name, value)}") + lines.append( + f"{escape_jinja_literal(str(key))} = {self._toml_value_expr(var_name, value)}" + ) else: - lines.append(f"{key} = {self._toml_value_expr(var_name, value)}") + lines.append( + f"{escape_jinja_literal(str(key))} = {self._toml_value_expr(var_name, value)}" + ) def walk(obj: dict[str, Any], path: tuple[str, ...] = ()) -> None: scalar_items = {k: v for k, v in obj.items() if not isinstance(v, dict)} nested_items = {k: v for k, v in obj.items() if isinstance(v, dict)} if path: - header = ".".join(path) + header = ".".join(escape_jinja_literal(str(p)) for p in path) lines.append(f"[{header}]") for key, val in scalar_items.items(): @@ -217,7 +235,7 @@ class TomlHandler(DictLikeHandler): # Blank or pure comment if not stripped or stripped.startswith("#"): - out_lines.append(raw_line) + out_lines.append(escape_jinja_literal(raw_line)) continue # Table header: [server] or [server.tls] or [[array.of.tables]] @@ -230,7 +248,7 @@ class TomlHandler(DictLikeHandler): inner = inner.strip("[]") # handle [[table]] as well parts = [p.strip() for p in inner.split(".") if p.strip()] current_table = tuple(parts) - out_lines.append(raw_line) + out_lines.append(escape_jinja_literal(raw_line)) continue # Try key = value @@ -245,7 +263,7 @@ class TomlHandler(DictLikeHandler): eq_index = content.find("=") if eq_index == -1: - out_lines.append(raw_line) + out_lines.append(escape_jinja_literal(raw_line)) continue before_eq = content[:eq_index] @@ -253,7 +271,7 @@ class TomlHandler(DictLikeHandler): key = before_eq.strip() if not key: - out_lines.append(raw_line) + out_lines.append(escape_jinja_literal(raw_line)) continue # Whitespace after '=' @@ -289,19 +307,23 @@ class TomlHandler(DictLikeHandler): nested_var = self.make_var_name(role_prefix, nested_path) if isinstance(sub_val, str): inner_bits.append( - f"{sub_key} = {self._toml_quoted_expr(nested_var)}" + f"{escape_jinja_literal(str(sub_key))} = {self._toml_quoted_expr(nested_var)}" ) elif isinstance(sub_val, bool): inner_bits.append( - f"{sub_key} = {self._toml_value_expr(nested_var, sub_val)}" + f"{escape_jinja_literal(str(sub_key))} = {self._toml_value_expr(nested_var, sub_val)}" ) else: inner_bits.append( - f"{sub_key} = {self._toml_value_expr(nested_var, sub_val)}" + f"{escape_jinja_literal(str(sub_key))} = {self._toml_value_expr(nested_var, sub_val)}" ) replacement_value = "{ " + ", ".join(inner_bits) + " }" new_content = ( - before_eq + "=" + leading_ws + replacement_value + comment_part + escape_jinja_literal(before_eq) + + "=" + + leading_ws + + replacement_value + + escape_jinja_literal(comment_part) ) out_lines.append(new_content + newline) continue @@ -327,7 +349,11 @@ class TomlHandler(DictLikeHandler): replacement_value = j2.variable(var_name) new_content = ( - before_eq + "=" + leading_ws + replacement_value + comment_part + escape_jinja_literal(before_eq) + + "=" + + leading_ws + + replacement_value + + escape_jinja_literal(comment_part) ) out_lines.append(new_content + newline) @@ -355,7 +381,7 @@ class TomlHandler(DictLikeHandler): if not stripped or stripped.startswith("#"): # Only output if we're not skipping if not skip_until_next_table: - out_lines.append(raw_line) + out_lines.append(escape_jinja_literal(raw_line)) continue # Table header: [server] or [server.tls] or [[array.of.tables]] @@ -404,7 +430,9 @@ class TomlHandler(DictLikeHandler): out_lines.append( f"{j2.for_start(item_var, collection_var)}\n" ) - out_lines.append(f"[[{'.'.join(table_path)}]]\n") + out_lines.append( + f"[[{'.'.join(escape_jinja_literal(str(p)) for p in table_path)}]]\n" + ) # Add fields from sample item for key, value in sample_item.items(): @@ -412,17 +440,17 @@ class TomlHandler(DictLikeHandler): continue if isinstance(value, str): out_lines.append( - f"{key} = " + f"{escape_jinja_literal(str(key))} = " f"{self._toml_quoted_expr(f'{item_var}.{key}')}\n" ) elif isinstance(value, bool): out_lines.append( - f"{key} = " + f"{escape_jinja_literal(str(key))} = " f"{self._toml_value_expr(f'{item_var}.{key}', value)}\n" ) else: out_lines.append( - f"{key} = " + f"{escape_jinja_literal(str(key))} = " f"{self._toml_value_expr(f'{item_var}.{key}', value)}\n" ) @@ -437,7 +465,7 @@ class TomlHandler(DictLikeHandler): skip_until_next_table = False current_table = table_path - out_lines.append(raw_line) + out_lines.append(escape_jinja_literal(raw_line)) continue # If we're inside a skipped array-of-tables section, skip this line @@ -456,7 +484,7 @@ class TomlHandler(DictLikeHandler): eq_index = content.find("=") if eq_index == -1: - out_lines.append(raw_line) + out_lines.append(escape_jinja_literal(raw_line)) continue before_eq = content[:eq_index] @@ -464,7 +492,7 @@ class TomlHandler(DictLikeHandler): key = before_eq.strip() if not key: - out_lines.append(raw_line) + out_lines.append(escape_jinja_literal(raw_line)) continue # Whitespace after '=' @@ -501,7 +529,11 @@ class TomlHandler(DictLikeHandler): replacement_value = j2.to_json(collection_var) new_content = ( - before_eq + "=" + leading_ws + replacement_value + comment_part + escape_jinja_literal(before_eq) + + "=" + + leading_ws + + replacement_value + + escape_jinja_literal(comment_part) ) out_lines.append(new_content + newline) continue @@ -526,19 +558,23 @@ class TomlHandler(DictLikeHandler): nested_var = self.make_var_name(role_prefix, nested_path) if isinstance(sub_val, str): inner_bits.append( - f"{sub_key} = {self._toml_quoted_expr(nested_var)}" + f"{escape_jinja_literal(str(sub_key))} = {self._toml_quoted_expr(nested_var)}" ) elif isinstance(sub_val, bool): inner_bits.append( - f"{sub_key} = {self._toml_value_expr(nested_var, sub_val)}" + f"{escape_jinja_literal(str(sub_key))} = {self._toml_value_expr(nested_var, sub_val)}" ) else: inner_bits.append( - f"{sub_key} = {self._toml_value_expr(nested_var, sub_val)}" + f"{escape_jinja_literal(str(sub_key))} = {self._toml_value_expr(nested_var, sub_val)}" ) replacement_value = "{ " + ", ".join(inner_bits) + " }" new_content = ( - before_eq + "=" + leading_ws + replacement_value + comment_part + escape_jinja_literal(before_eq) + + "=" + + leading_ws + + replacement_value + + escape_jinja_literal(comment_part) ) out_lines.append(new_content + newline) continue @@ -564,7 +600,11 @@ class TomlHandler(DictLikeHandler): replacement_value = j2.variable(var_name) new_content = ( - before_eq + "=" + leading_ws + replacement_value + comment_part + escape_jinja_literal(before_eq) + + "=" + + leading_ws + + replacement_value + + escape_jinja_literal(comment_part) ) out_lines.append(new_content + newline) diff --git a/src/jinjaturtle/handlers/xml.py b/src/jinjaturtle/handlers/xml.py index 51c7a73..9fde3ec 100644 --- a/src/jinjaturtle/handlers/xml.py +++ b/src/jinjaturtle/handlers/xml.py @@ -7,6 +7,7 @@ import xml.etree.ElementTree as ET # nosec from .base import BaseHandler from .. import j2 +from ..escape import escape_jinja_literal from ..loop_analyzer import LoopCandidate @@ -230,6 +231,37 @@ class XmlHandler(BaseHandler): walk(root, ()) + # Internal marker prefixes used by JinjaTurtle's own comment nodes. These + # must NOT be escaped (they are converted into real Jinja control structures + # downstream). Source-file comments have none of these prefixes. + _MARKER_PREFIXES = ("LOOP:", "IF:", "ENDIF:") + + def _is_jt_marker(self, comment_text: str) -> bool: + stripped = (comment_text or "").lstrip() + return any(stripped.startswith(p) for p in self._MARKER_PREFIXES) + + def _escape_source_comments(self, root: ET.Element) -> None: + """Escape template metacharacters in comments preserved from the source. + + XML comments are re-emitted verbatim by ``ET.tostring`` (the tree is + parsed with ``insert_comments=True``). Attacker-controlled comment text + such as ```` would otherwise become live + template code. Element/attribute *names* cannot carry Jinja delimiters + (XML naming rules forbid the characters and the parser rejects them), and + text/attribute *values* are already replaced with ``{{ var }}`` + placeholders, so comments (and the prolog, handled separately) are the + only XML injection vector. + + JinjaTurtle's own internal marker comments are left untouched so they can + be converted into real loops/conditionals later. + """ + # ET represents comments with a callable tag (ET.Comment). Iterate all + # descendants and escape comment text that is not one of our markers. + for elem in root.iter(): + if elem.tag is ET.Comment: + if not self._is_jt_marker(elem.text or ""): + elem.text = escape_jinja_literal(elem.text or "") + def _generate_xml_template_from_text(self, role_prefix: str, text: str) -> str: """Generate scalar-only Jinja2 template.""" prolog, body = self._split_xml_prolog(text) @@ -240,12 +272,16 @@ class XmlHandler(BaseHandler): self._apply_jinja_to_xml_tree(role_prefix, root) + # Neutralise template metacharacters in any comments preserved from the + # source file before serialising. + self._escape_source_comments(root) + indent = getattr(ET, "indent", None) if indent is not None: indent(root, space=" ") # type: ignore[arg-type] xml_body = ET.tostring(root, encoding="unicode") - return prolog + xml_body + return escape_jinja_literal(prolog) + xml_body def _generate_xml_template_with_loops_from_text( self, @@ -265,6 +301,11 @@ class XmlHandler(BaseHandler): # Apply Jinja transformations (including loop markers) self._apply_jinja_to_xml_tree(role_prefix, root, loop_candidates) + # Escape comments preserved from the source. JinjaTurtle's own + # LOOP/IF/ENDIF marker comments are recognised and left intact so they + # can be converted into real Jinja control structures below. + self._escape_source_comments(root) + # Convert to string indent = getattr(ET, "indent", None) if indent is not None: @@ -275,7 +316,7 @@ class XmlHandler(BaseHandler): # Post-process to replace loop markers with actual Jinja loops xml_body = self._insert_xml_loops(xml_body, role_prefix, loop_candidates, root) - return prolog + xml_body + return escape_jinja_literal(prolog) + xml_body def _insert_xml_loops( self, diff --git a/src/jinjaturtle/handlers/yaml.py b/src/jinjaturtle/handlers/yaml.py index 1ad9bf3..d8131b0 100644 --- a/src/jinjaturtle/handlers/yaml.py +++ b/src/jinjaturtle/handlers/yaml.py @@ -6,6 +6,7 @@ from typing import Any from .dict import DictLikeHandler from .. import j2 +from ..escape import escape_jinja_literal from ..loop_analyzer import LoopCandidate @@ -102,7 +103,7 @@ class YamlHandler(DictLikeHandler): indent = len(raw_line) - len(stripped) if not stripped or stripped.startswith("#"): - out_lines.append(raw_line) + out_lines.append(escape_jinja_literal(raw_line)) continue while stack and indent < stack[-1][0]: @@ -112,7 +113,7 @@ class YamlHandler(DictLikeHandler): key_part, rest = stripped.split(":", 1) key = key_part.strip() if not key: - out_lines.append(raw_line) + out_lines.append(escape_jinja_literal(raw_line)) continue rest_stripped = rest.lstrip(" \t") @@ -125,7 +126,7 @@ class YamlHandler(DictLikeHandler): stack.append((indent, path, "map")) if not has_value: - out_lines.append(raw_line) + out_lines.append(escape_jinja_literal(raw_line)) continue value_part, comment_part = self._split_inline_comment( @@ -147,8 +148,8 @@ class YamlHandler(DictLikeHandler): replacement = self._yaml_scalar_expr(var_name, raw_value) leading = rest[: len(rest) - len(rest.lstrip(" \t"))] - new_rest = f"{leading}{replacement}{comment_part}" - new_stripped = f"{key}:{new_rest}" + new_rest = f"{leading}{replacement}{escape_jinja_literal(comment_part)}" + new_stripped = f"{escape_jinja_literal(key)}:{new_rest}" out_lines.append( " " * indent + new_stripped @@ -185,7 +186,7 @@ class YamlHandler(DictLikeHandler): else: replacement = self._yaml_scalar_expr(var_name, raw_value) - new_stripped = f"- {replacement}{comment_part}" + new_stripped = f"- {replacement}{escape_jinja_literal(comment_part)}" out_lines.append( " " * indent + new_stripped @@ -193,7 +194,7 @@ class YamlHandler(DictLikeHandler): ) continue - out_lines.append(raw_line) + out_lines.append(escape_jinja_literal(raw_line)) return "".join(out_lines) @@ -275,7 +276,7 @@ class YamlHandler(DictLikeHandler): next_line = next_significant_line(line_index) if next_line is None: skip_until_indent = None - out_lines.append(raw_line) + out_lines.append(escape_jinja_literal(raw_line)) else: next_indent, next_stripped = next_line still_in_collection = next_indent > skip_until_indent or ( @@ -284,12 +285,12 @@ class YamlHandler(DictLikeHandler): ) if not still_in_collection: skip_until_indent = None - out_lines.append(raw_line) + out_lines.append(escape_jinja_literal(raw_line)) continue if is_comment: if indent <= skip_until_indent: skip_until_indent = None - out_lines.append(raw_line) + out_lines.append(escape_jinja_literal(raw_line)) # Comments/blank lines indented beneath the replaced # collection are considered part of that collection and # cannot be placed safely inside a generated loop. @@ -303,7 +304,7 @@ class YamlHandler(DictLikeHandler): # Blank or comment lines if is_blank or is_comment: - out_lines.append(raw_line) + out_lines.append(escape_jinja_literal(raw_line)) continue # Adjust stack based on indent @@ -315,7 +316,7 @@ class YamlHandler(DictLikeHandler): key_part, rest = stripped.split(":", 1) key = key_part.strip() if not key: - out_lines.append(raw_line) + out_lines.append(escape_jinja_literal(raw_line)) continue rest_stripped = rest.lstrip(" \t") @@ -353,7 +354,7 @@ class YamlHandler(DictLikeHandler): continue if not has_value: - out_lines.append(raw_line) + out_lines.append(escape_jinja_literal(raw_line)) continue # Scalar value - replace with variable @@ -376,8 +377,8 @@ class YamlHandler(DictLikeHandler): replacement = self._yaml_scalar_expr(var_name, raw_value) leading = rest[: len(rest) - len(rest.lstrip(" \t"))] - new_rest = f"{leading}{replacement}{comment_part}" - new_stripped = f"{key}:{new_rest}" + new_rest = f"{leading}{replacement}{escape_jinja_literal(comment_part)}" + new_stripped = f"{escape_jinja_literal(key)}:{new_rest}" out_lines.append( " " * indent + new_stripped @@ -439,7 +440,7 @@ class YamlHandler(DictLikeHandler): else: replacement = self._yaml_scalar_expr(var_name, raw_value) - new_stripped = f"- {replacement}{comment_part}" + new_stripped = f"- {replacement}{escape_jinja_literal(comment_part)}" out_lines.append( " " * indent + new_stripped @@ -447,7 +448,7 @@ class YamlHandler(DictLikeHandler): ) continue - out_lines.append(raw_line) + out_lines.append(escape_jinja_literal(raw_line)) return "".join(out_lines) @@ -480,7 +481,7 @@ class YamlHandler(DictLikeHandler): lines: list[str] = [] if not is_list: key = candidate.path[-1] if candidate.path else "items" - lines.append(f"{indent_str}{key}:") + lines.append(f"{indent_str}{escape_jinja_literal(str(key))}:") item_lines: list[str] = [] if candidate.items: @@ -549,12 +550,16 @@ class YamlHandler(DictLikeHandler): if first_key and is_list_item: # First key gets the list marker value_expr = self._yaml_value_expr(f"{loop_var}.{key}", value) - lines.append(f"{indent_str}- {key}: {value_expr}") + lines.append( + f"{indent_str}- {escape_jinja_literal(str(key))}: {value_expr}" + ) first_key = False else: # Subsequent keys are indented sub_indent = indent + 2 if is_list_item else indent value_expr = self._yaml_value_expr(f"{loop_var}.{key}", value) - lines.append(f"{' ' * sub_indent}{key}: {value_expr}") + lines.append( + f"{' ' * sub_indent}{escape_jinja_literal(str(key))}: {value_expr}" + ) return lines diff --git a/tests/test_injection_security.py b/tests/test_injection_security.py new file mode 100644 index 0000000..642c0b8 --- /dev/null +++ b/tests/test_injection_security.py @@ -0,0 +1,212 @@ +"""Security regression tests for template injection (SSTI). + +JinjaTurtle copies parts of the source config (comments, unrecognised lines, +structural keys) verbatim into the generated template. If that text contains +Jinja2/ERB delimiters it must be neutralised, otherwise attacker-influenced +config content becomes live template code that executes when Salt/Ansible/Puppet +later renders the template. + +These tests render the *generated* template the way a downstream tool would and +assert that an injected payload never executes. A tripwire object is exposed +under every name a payload might reference; if the rendered output ever contains +the tripwire sentinel, an injected expression executed and the test fails. +""" + +from __future__ import annotations + +import re +import subprocess +import sys +from pathlib import Path + +import jinja2 +import pytest +import yaml as pyyaml + +from jinjaturtle.escape import escape_jinja_literal, escape_erb_literal + + +TRIP = "__TRIPWIRE_FIRED__" + + +class _Boom: + """Returns the tripwire sentinel for any access/call an SSTI payload makes.""" + + def run(self, *a, **k): + return TRIP + + def __call__(self, *a, **k): + return TRIP + + def __getitem__(self, k): + return self + + def __getattr__(self, n): + return _Boom() + + def __str__(self): + return TRIP + + +def _render_jinja(template_text: str, defaults: dict) -> str: + env = jinja2.Environment(undefined=jinja2.ChainableUndefined) + env.filters.setdefault("to_json", lambda v, **k: __import__("json").dumps(v)) + env.filters.setdefault("lower", lambda v: str(v).lower()) + ctx = dict(defaults or {}) + for name in ("salt", "cmd", "os", "subprocess", "cycler", "lipsum", "namespace"): + ctx.setdefault(name, _Boom()) + return env.from_string(template_text).render(**ctx) + + +def _run_jinjaturtle(tmp_path: Path, source_name: str, body: str, fmt: str): + src = tmp_path / source_name + src.write_text(body, encoding="utf-8") + tpl = tmp_path / "out.tpl" + dfl = tmp_path / "defaults.yml" + res = subprocess.run( + [ + sys.executable, + "-m", + "jinjaturtle.cli", + str(src), + "-f", + fmt, + "--role-name", + "role", + "-t", + str(tpl), + "-d", + str(dfl), + ], + capture_output=True, + text=True, + ) + assert res.returncode == 0, f"generation failed: {res.stderr}" + defaults = pyyaml.safe_load(dfl.read_text()) or {} + return tpl.read_text(), defaults + + +# A representative payload for each format, placed where the format allows +# attacker-controlled verbatim text (comments / unrecognised lines). +FORMAT_CASES = [ + ( + "ini", + "evil.ini", + "[s]\n" + "good = ok ; {{ salt['cmd.run']('id') }}\n" + "# {{ cmd.run('whoami') }}\n", + ), + ( + "yaml", + "evil.yaml", + "server:\n" " motd: ok\n" " # {{ salt['cmd.run']('id') }}\n", + ), + ( + "toml", + "evil.toml", + "[s]\n" 'good = "ok"\n' "# {{ cmd.run('id') }}\n", + ), + ( + "xml", + "evil.xml", + "\n" + " \n" + ' ok\n' + "\n", + ), + ( + "postfix", + "main.cf", + "myhostname = mail.example.com\n" "# {{ salt['cmd.run']('id') }}\n", + ), + ( + "systemd", + "evil.service", + "[Unit]\n" + "Description=ok\n" + "# {{ cmd.run('id') }}\n" + "RawLineNoEquals {% for x in ().__class__.__bases__ %}\n" + "[Service]\n" + "ExecStart=/bin/true\n", + ), + ( + "ssh", + "sshd_config", + "# {{ salt['cmd.run']('id') }}\n" "Port 22\n" "PermitRootLogin no\n", + ), +] + + +@pytest.mark.parametrize("fmt,name,body", FORMAT_CASES) +def test_comment_payload_does_not_execute(tmp_path, fmt, name, body): + template_text, defaults = _run_jinjaturtle(tmp_path, name, body, fmt) + rendered = _render_jinja(template_text, defaults) + assert TRIP not in rendered, f"injected payload executed for {fmt}:\n{rendered}" + + +@pytest.mark.parametrize("fmt,name,body", FORMAT_CASES) +def test_generated_template_is_renderable(tmp_path, fmt, name, body): + # A correct escape must still produce a syntactically valid template. + template_text, defaults = _run_jinjaturtle(tmp_path, name, body, fmt) + # Should not raise a TemplateSyntaxError. + _render_jinja(template_text, defaults) + + +# --- Unit-level guarantees for the escaper itself --------------------------- + +SSTI_PAYLOADS = [ + "{{ 7*7 }}", + "{{ salt['cmd.run']('id') }}", + "{% set x = cycler.__init__.__globals__ %}{{ x }}", + "{# comment payload #}", + "text {% endraw %} breakout {{ evil }}", + "nested {% endraw %} spacing {{ evil }}", + "{%- endraw -%}{{ evil }}", + "mixed {{ a }} and {% b %} and {# c #}", + "}}{{ orphan delimiters %}{%", +] + + +@pytest.mark.parametrize("payload", SSTI_PAYLOADS) +def test_escape_jinja_literal_renders_back_to_original(payload): + """Escaped text must render to the exact original characters, inertly.""" + env = jinja2.Environment(undefined=jinja2.ChainableUndefined) + escaped = escape_jinja_literal(payload) + rendered = env.from_string(escaped).render(evil="EVIL", x="X", a="A") + assert rendered == payload + assert TRIP not in rendered + + +def test_escape_jinja_literal_noop_on_plain_text(): + for plain in ["", "hello world", "# a normal comment", "port = 8080", "key: value"]: + assert escape_jinja_literal(plain) == plain + + +def test_escape_jinja_literal_actually_blocks_execution(): + env = jinja2.Environment(undefined=jinja2.ChainableUndefined) + payload = "{{ boom.run('x') }}" + escaped = escape_jinja_literal(payload) + rendered = env.from_string(escaped).render(boom=_Boom()) + assert TRIP not in rendered + # Sanity: the *unescaped* payload would have fired the tripwire. + fired = env.from_string(payload).render(boom=_Boom()) + assert TRIP in fired + + +@pytest.mark.parametrize( + "payload", + [ + "<%= system('id') %>", + "<% require 'open3' %>", + "text <%= 1+1 %> more", + "-%> orphan <%", + ], +) +def test_escape_erb_literal_removes_executable_tags(payload): + escaped = escape_erb_literal(payload) + # No raw executable ERB tag should survive that contains the original code. + live = re.findall(r"<%[-=#]?(.*?)-?%>", escaped, re.S) + for chunk in live: + assert "system" not in chunk + assert "require" not in chunk + # Numeric/expression payloads must be reduced to literal-string prints. From 15770c8e3d3129d23a20024cce3c89f31953af41 Mon Sep 17 00:00:00 2001 From: Miguel Jacq Date: Tue, 23 Jun 2026 14:30:42 +1000 Subject: [PATCH 05/25] Upgrade to poetry2 and update dependencies --- .forgejo/workflows/ci.yml | 20 +++- poetry.lock | 239 ++++++++++++++++++++------------------ pyproject.toml | 40 ++++--- 3 files changed, 165 insertions(+), 134 deletions(-) diff --git a/.forgejo/workflows/ci.yml b/.forgejo/workflows/ci.yml index d503028..0773dbb 100644 --- a/.forgejo/workflows/ci.yml +++ b/.forgejo/workflows/ci.yml @@ -17,13 +17,29 @@ jobs: DEBIAN_FRONTEND=noninteractive apt-get install -y --no-install-recommends python3-venv pipx - name: Install Poetry + env: + PYTHON_BIN: ${{ matrix.python }} + POETRY_VERSION: "2.4.1" run: | - pipx install poetry==1.8.3 - /root/.local/bin/poetry --version + set -eux + if ! command -v pipx >/dev/null 2>&1; then + "${PYTHON_BIN}" -m pip install --user pipx + fi + PIPX_BIN="$(command -v pipx || true)" + if [ -z "${PIPX_BIN}" ]; then + PIPX_BIN="${HOME}/.local/bin/pipx" + fi + "${PIPX_BIN}" install --python "${PYTHON_BIN}" "poetry==${POETRY_VERSION}" echo "$HOME/.local/bin" >> "$GITHUB_PATH" + export PATH="$HOME/.local/bin:$PATH" + poetry --version + poetry --version | grep -E "Poetry \(version 2\." - name: Install project deps (including test extras) + env: + PYTHON_BIN: ${{ matrix.python }} run: | + poetry env use "${PYTHON_BIN}" poetry install --with dev - name: Run test script diff --git a/poetry.lock b/poetry.lock index bc7ba3d..9bfef74 100644 --- a/poetry.lock +++ b/poetry.lock @@ -1,4 +1,4 @@ -# This file is automatically @generated by Poetry 1.8.3 and should not be changed by hand. +# This file is automatically @generated by Poetry 2.4.1 and should not be changed by hand. [[package]] name = "certifi" @@ -6,6 +6,7 @@ version = "2026.6.17" description = "Python package for providing Mozilla's CA Bundle." optional = false python-versions = ">=3.7" +groups = ["dev"] files = [ {file = "certifi-2026.6.17-py3-none-any.whl", hash = "sha256:2227dcbaafe0d2f59279d1762ddddc37783ed4354594f194ffc31d20f41fc3db"}, {file = "certifi-2026.6.17.tar.gz", hash = "sha256:024c88eeec92ca068db80f02b8b07c9cef7b9fe261d1d535abfd5abd6f6af432"}, @@ -17,6 +18,7 @@ version = "3.4.7" description = "The Real First Universal Charset Detector. Open, modern and actively maintained alternative to Chardet." optional = false python-versions = ">=3.7" +groups = ["dev"] files = [ {file = "charset_normalizer-3.4.7-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:cdd68a1fb318e290a2077696b7eb7a21a49163c455979c639bf5a5dcdc46617d"}, {file = "charset_normalizer-3.4.7-cp310-cp310-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:e17b8d5d6a8c47c85e68ca8379def1303fd360c3e22093a807cd34a71cd082b8"}, @@ -155,6 +157,8 @@ version = "0.4.6" description = "Cross-platform colored terminal text." optional = false python-versions = "!=3.0.*,!=3.1.*,!=3.2.*,!=3.3.*,!=3.4.*,!=3.5.*,!=3.6.*,>=2.7" +groups = ["dev"] +markers = "sys_platform == \"win32\"" files = [ {file = "colorama-0.4.6-py2.py3-none-any.whl", hash = "sha256:4f1d9991f5acc0ca119f9d443620b77f9d6b33703e51011c16baf57afb285fc6"}, {file = "colorama-0.4.6.tar.gz", hash = "sha256:08695f5cb7ed6e0531a20572697297273c47b8cae5a63ffc6d6ed5c201be6e44"}, @@ -162,124 +166,110 @@ files = [ [[package]] name = "coverage" -version = "7.14.1" +version = "7.14.3" description = "Code coverage measurement for Python" optional = false python-versions = ">=3.10" +groups = ["dev"] files = [ - {file = "coverage-7.14.1-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:3e3680291c4a1d0dadfa84a2c459576a4af5133abb617905714339a0c73138cf"}, - {file = "coverage-7.14.1-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:a5274669f37f2343635a347b91a60777621341ab3378e9c6ac9335eee704bddf"}, - {file = "coverage-7.14.1-cp310-cp310-manylinux1_i686.manylinux_2_28_i686.manylinux_2_5_i686.whl", hash = "sha256:cfe5a5fec635799ef33428f1e5e61bafa45a92a96190ba731561ba558ccc214d"}, - {file = "coverage-7.14.1-cp310-cp310-manylinux1_x86_64.manylinux_2_28_x86_64.manylinux_2_5_x86_64.whl", hash = "sha256:62a9f70b52e0b5a95cfef4a5c5641b06983cadc5e538a3feeb5c00211f523ac2"}, - {file = "coverage-7.14.1-cp310-cp310-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:3c18ebc343e15be53049b3a2dce38fe82d58f37e20ab9094b3a39c0aa4f6bb47"}, - {file = "coverage-7.14.1-cp310-cp310-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:b84ffdf877644e7096aa936991efeed873f7f3df57b9cd001312b7668ab08550"}, - {file = "coverage-7.14.1-cp310-cp310-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:e854312c4103f2ad4c0dc023b69b77ebfd2c89db5f86c4c94dc2353f9a92167e"}, - {file = "coverage-7.14.1-cp310-cp310-musllinux_1_2_aarch64.whl", hash = "sha256:c643734307300234fafa36bf2a040a7235f8f177ea1fd6ec1423aea6fb7b929f"}, - {file = "coverage-7.14.1-cp310-cp310-musllinux_1_2_i686.whl", hash = "sha256:84ac9499e48700399a5dd0ea7085b5091961fec52c68d66b4ec0d3cf7f4441b1"}, - {file = "coverage-7.14.1-cp310-cp310-musllinux_1_2_ppc64le.whl", hash = "sha256:7f02d09f70776579b926d889a4c9c235070a1f47c40458aeaca563fae5acfdb5"}, - {file = "coverage-7.14.1-cp310-cp310-musllinux_1_2_riscv64.whl", hash = "sha256:ce66d8e46da2bb5ee313a745cbd2e391d319176c1f7a9451bfcd3a2fb920859b"}, - {file = "coverage-7.14.1-cp310-cp310-musllinux_1_2_x86_64.whl", hash = "sha256:c912c259304cfb5ee584481cfb7ce1ff932b4d61e6c9140b8f19cb7b5ed82332"}, - {file = "coverage-7.14.1-cp310-cp310-win32.whl", hash = "sha256:1238cb94638e610e972c60dac68e813f868dc7d6e982535270558443058d9d59"}, - {file = "coverage-7.14.1-cp310-cp310-win_amd64.whl", hash = "sha256:fc459e5d73be2d6332fcfe8dbf3d8994671fe33c700f4565988ecfa511547253"}, - {file = "coverage-7.14.1-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:478b5bcd63c2e1357c5c7e16c070690df7b07f676b1c114d7b93e533c664309f"}, - {file = "coverage-7.14.1-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:a24a81f9715ee42ef59a316cc11611c98fe23920f7c81861315c9f3ff4a230f4"}, - {file = "coverage-7.14.1-cp311-cp311-manylinux1_i686.manylinux_2_28_i686.manylinux_2_5_i686.whl", hash = "sha256:196a13319ad88d6d8ef5ab489ec4f44ddde2143c0c7d5b27786f6c3ffd56a7e1"}, - {file = "coverage-7.14.1-cp311-cp311-manylinux1_x86_64.manylinux_2_28_x86_64.manylinux_2_5_x86_64.whl", hash = "sha256:3d452fd08b5c72c5167c93e6867b5c08500bd40f2a21e1e854a500550b6cc36f"}, - {file = "coverage-7.14.1-cp311-cp311-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:23bf7fa51ac02e07fc7c96849b82946da47ae862dc8f86d183b2a4864fc38129"}, - {file = "coverage-7.14.1-cp311-cp311-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:bcaa50684dcaadfa599ac48f81103c756d791cfd85c97203d2217c593d48b860"}, - {file = "coverage-7.14.1-cp311-cp311-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:4ea1c034f95c9b056e856b794630b17f9fa3d57e4800ff1e503d3be0f9c9078c"}, - {file = "coverage-7.14.1-cp311-cp311-musllinux_1_2_aarch64.whl", hash = "sha256:c7e057326434e441306226fbeb5d1aaf14a2637efe97ba668306635835f32ad7"}, - {file = "coverage-7.14.1-cp311-cp311-musllinux_1_2_i686.whl", hash = "sha256:59baf88468dbc8d63b1887afd92bda52e40bb1561696e5819670601403810cec"}, - {file = "coverage-7.14.1-cp311-cp311-musllinux_1_2_ppc64le.whl", hash = "sha256:d34d75f892b3ab73ba11cab5442cce7b3e168fd64162b16f0e1e0d09c508edef"}, - {file = "coverage-7.14.1-cp311-cp311-musllinux_1_2_riscv64.whl", hash = "sha256:3a56abc20a472baf0304c455721bc601477440d28ecfde8a03dde79ede07e0df"}, - {file = "coverage-7.14.1-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:6a3cb83d1552c0cd1b4906655b6a33fd4a8473229633a901c6b73bf86914dee9"}, - {file = "coverage-7.14.1-cp311-cp311-win32.whl", hash = "sha256:10274a1fbeb8ec5d72966e17bb198a3104257aca4ac09d98667c5f8aca8c8548"}, - {file = "coverage-7.14.1-cp311-cp311-win_amd64.whl", hash = "sha256:87ebdf787d4888e3f3f2d523eadc6e18c6d18c6d0eb173801a189641627fb37e"}, - {file = "coverage-7.14.1-cp311-cp311-win_arm64.whl", hash = "sha256:dd34767fa19848d35659ffc0a75314f58c7af3f1cd87ec521e8292a1238398a3"}, - {file = "coverage-7.14.1-cp312-cp312-macosx_10_13_x86_64.whl", hash = "sha256:a06c76364a9360e33d6d23769aefdf7f66f38e2ffb60ceb1baaa4989d83b695c"}, - {file = "coverage-7.14.1-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:fad54e871165f6ec2f536063ac74c3104508a12963e64072ba44bd822de52b0c"}, - {file = "coverage-7.14.1-cp312-cp312-manylinux1_i686.manylinux_2_28_i686.manylinux_2_5_i686.whl", hash = "sha256:84b535f00655ecafe1d929d1fb00ed5d6fa3051ea643ab2c161a3887b86f294b"}, - {file = "coverage-7.14.1-cp312-cp312-manylinux1_x86_64.manylinux_2_28_x86_64.manylinux_2_5_x86_64.whl", hash = "sha256:6b6b0853b895fe0e98cbfc580d1ec3393d9302b4b1e96a77b3f5c91fdab899e6"}, - {file = "coverage-7.14.1-cp312-cp312-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:442cc9c952b2df400cda54bb04ab87330cf2cd08a8692cbbea36773531eb6f37"}, - {file = "coverage-7.14.1-cp312-cp312-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:8270544c361ed405a27a060dbc9ed2c124b084d96dfdc2d9a2510482aef981ad"}, - {file = "coverage-7.14.1-cp312-cp312-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:48b283b1dd6372e8de2a7a9a4c4d5dc06f4d4fd209b876f3c88a7a205a0c8f84"}, - {file = "coverage-7.14.1-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:5b0c99ba93a07d56f6df340bb79be53202a082b2fdb81bfe6190b741a3470d54"}, - {file = "coverage-7.14.1-cp312-cp312-musllinux_1_2_i686.whl", hash = "sha256:e471bc5769ff073b058cfadb0d736b56ce067c8560eabeb0da88462df98c23e7"}, - {file = "coverage-7.14.1-cp312-cp312-musllinux_1_2_ppc64le.whl", hash = "sha256:f497a1ea81d4cd7c10ddcaa685135b9aabd291af3d55775a9ddf3cb7a364cdd9"}, - {file = "coverage-7.14.1-cp312-cp312-musllinux_1_2_riscv64.whl", hash = "sha256:2222be86d0b54f5dd5a38f45f17f315f737245e857bf0bdedc70734f84a13c02"}, - {file = "coverage-7.14.1-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:85e85586565842f6932abebd4c18bcb1074223dc0b3576e7d173ca710622813a"}, - {file = "coverage-7.14.1-cp312-cp312-win32.whl", hash = "sha256:4a28fd227808366b196a75476dced2eb35b351d6766ba9c858dc93319e87f4f1"}, - {file = "coverage-7.14.1-cp312-cp312-win_amd64.whl", hash = "sha256:54acdb6674a4661768d7bf7db32dfb9f46ab1d764f8aba6df75ce1a6a088724e"}, - {file = "coverage-7.14.1-cp312-cp312-win_arm64.whl", hash = "sha256:99cd41ff91afd94896fea3bc002706b6ae4ce95727d06e4a0f39c0a8d8bd8b1a"}, - {file = "coverage-7.14.1-cp313-cp313-macosx_10_13_x86_64.whl", hash = "sha256:be9f2c802dcfce3f71298303aa5dad0dce440a76c52f2f60dacd8656dab78793"}, - {file = "coverage-7.14.1-cp313-cp313-macosx_11_0_arm64.whl", hash = "sha256:6223a72fd0e4c7156353ec0f08a5f93623e1d3034d0e2683b9bb8ea674131b1d"}, - {file = "coverage-7.14.1-cp313-cp313-manylinux1_i686.manylinux_2_28_i686.manylinux_2_5_i686.whl", hash = "sha256:7279d2110a28cebc738b6459ecda2771735a4c18465fbbd36b3288fe5ed92247"}, - {file = "coverage-7.14.1-cp313-cp313-manylinux1_x86_64.manylinux_2_28_x86_64.manylinux_2_5_x86_64.whl", hash = "sha256:9eeb3fcbc13ba40dfbdb22d01d196a28e9cef9ed4c29b60061a1e0e823a9929d"}, - {file = "coverage-7.14.1-cp313-cp313-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:5f0cfc27c539f07cf5c0a4cfe211d0b6cae039f8f40526dbaa71944e64b50a7b"}, - {file = "coverage-7.14.1-cp313-cp313-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:221c70f316241a78e77e607c227cefc8808d4e08f28d99c04f35694690e940be"}, - {file = "coverage-7.14.1-cp313-cp313-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:da028256b04ec30e5e0114b6f76172938c313991f0a2d3d894271315cf5d5e43"}, - {file = "coverage-7.14.1-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:76a085d7005236a767e3426148b2c407e53ad61695c562f8a81da2d373324901"}, - {file = "coverage-7.14.1-cp313-cp313-musllinux_1_2_i686.whl", hash = "sha256:b553d04b5e778a8e56d57eb134aff42a92718ecba45e79c4764ecfa40efd92ff"}, - {file = "coverage-7.14.1-cp313-cp313-musllinux_1_2_ppc64le.whl", hash = "sha256:46f714d2fb8ae2f4f29f23ada7f1e79b759fff5a70f94a1dac23af204c3ec9e4"}, - {file = "coverage-7.14.1-cp313-cp313-musllinux_1_2_riscv64.whl", hash = "sha256:1896f5e19ff3f0431c7ce2172adc54890fd97f86b59ced8ca1649145d9ffe35d"}, - {file = "coverage-7.14.1-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:62fd185ef9df3c33d1c8178c5af105f762afbad96038de9a4ae100aa6297ca33"}, - {file = "coverage-7.14.1-cp313-cp313-win32.whl", hash = "sha256:ab4af6352741a604c431c6072fce5bee33bf0f20dc7a56618d6bf6bb89e9810c"}, - {file = "coverage-7.14.1-cp313-cp313-win_amd64.whl", hash = "sha256:7af486dabe8954d03b087f0021540897afe084f04e16ff5579e08cc46f871416"}, - {file = "coverage-7.14.1-cp313-cp313-win_arm64.whl", hash = "sha256:2224f89ffd0c5605ccce1ed7a584da162bc7c55f601ab1c946bc9de31a486b42"}, - {file = "coverage-7.14.1-cp313-cp313t-macosx_10_13_x86_64.whl", hash = "sha256:de286598cc65d2b489411174b1faec2f5a7775fb3201fd925db2a76b4030f37d"}, - {file = "coverage-7.14.1-cp313-cp313t-macosx_11_0_arm64.whl", hash = "sha256:042c46ded7c288aeb07cf14a28b6c1e10b78fcba40171c3fa1e939377eeef0b5"}, - {file = "coverage-7.14.1-cp313-cp313t-manylinux1_i686.manylinux_2_28_i686.manylinux_2_5_i686.whl", hash = "sha256:f4ddbe407477f04c45115d1a4e5bc480f753553b534d338d4c3358b1cdd0ea52"}, - {file = "coverage-7.14.1-cp313-cp313t-manylinux1_x86_64.manylinux_2_28_x86_64.manylinux_2_5_x86_64.whl", hash = "sha256:d13e6725992e2d2fd7d81d4f5241952d13740121dfd501da09201be39b2c003a"}, - {file = "coverage-7.14.1-cp313-cp313t-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:f747dc8edcfe740130f28f32f3995e955494285717e86ee25af51db2219df08a"}, - {file = "coverage-7.14.1-cp313-cp313t-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:ced2f09ef276fd58611a1ef502164ad266d2b75174e5a40cabbdb4033f9f6cf2"}, - {file = "coverage-7.14.1-cp313-cp313t-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:b84800013769a78ccb9ef4659402e26d06867e337b61ec365f77ad008adea80e"}, - {file = "coverage-7.14.1-cp313-cp313t-musllinux_1_2_aarch64.whl", hash = "sha256:ea8cd6ca0ee9f616aaef3afc6882e32c2cbf18b00d96313ffd76af650574034d"}, - {file = "coverage-7.14.1-cp313-cp313t-musllinux_1_2_i686.whl", hash = "sha256:aa5e304a873fabddc11e484e9b6b738bd38bd7bed17b09aa84eecf5332e8b8bb"}, - {file = "coverage-7.14.1-cp313-cp313t-musllinux_1_2_ppc64le.whl", hash = "sha256:5a1c5215be81035e629d5bc756650634d0bf31991038db7a0eccb90f025ce16d"}, - {file = "coverage-7.14.1-cp313-cp313t-musllinux_1_2_riscv64.whl", hash = "sha256:79058c47dae6788504b5effb319961bcd72d7240551464b91d474bc0ed186d69"}, - {file = "coverage-7.14.1-cp313-cp313t-musllinux_1_2_x86_64.whl", hash = "sha256:370c5afae3fa0658e11694a32b24c2778f6bc2d17718121f94ee185e69f26b54"}, - {file = "coverage-7.14.1-cp313-cp313t-win32.whl", hash = "sha256:3758dd0a7f1fa57365ef2e781df0f0731d38b6e3772259d13dae4bd8a958d4b1"}, - {file = "coverage-7.14.1-cp313-cp313t-win_amd64.whl", hash = "sha256:6ff665fb023a77386fe11685190cee1f60a7d635994a30d9b0a061533d470fce"}, - {file = "coverage-7.14.1-cp313-cp313t-win_arm64.whl", hash = "sha256:17a5a241e5997621a956a7f402a7433ef4221e5152809b785bec79e2323799f1"}, - {file = "coverage-7.14.1-cp314-cp314-macosx_10_15_x86_64.whl", hash = "sha256:d5ed429d0b8edaac649e889b4ffcedb6c80b06629a3f93050e3dddfb99235bee"}, - {file = "coverage-7.14.1-cp314-cp314-macosx_11_0_arm64.whl", hash = "sha256:8011224a62280e50dab346960c03cf47aca1a1e09e608c0fb33fd6e0cc8e9500"}, - {file = "coverage-7.14.1-cp314-cp314-manylinux1_i686.manylinux_2_28_i686.manylinux_2_5_i686.whl", hash = "sha256:12c42ec1e14f553c4f817e989365982e646e27211f10a0f717855b94a79c8906"}, - {file = "coverage-7.14.1-cp314-cp314-manylinux1_x86_64.manylinux_2_28_x86_64.manylinux_2_5_x86_64.whl", hash = "sha256:06144cd511cf2624873a035c5069cf297144f6e77a73ee3d7a55b605ec5efb42"}, - {file = "coverage-7.14.1-cp314-cp314-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:a311d8e1da24be5c1ccf85cbfb06315dbaa1703d5a1eab3f6432c72b837917c8"}, - {file = "coverage-7.14.1-cp314-cp314-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:c79cead5b5bc584d9c71451cb984d0e3a84e0c0937379c8efcbf27c8d661b851"}, - {file = "coverage-7.14.1-cp314-cp314-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:dcbf65f1f66a26cdd88c35cf68fb4729c5d1cd2e88added72420541dfb212034"}, - {file = "coverage-7.14.1-cp314-cp314-musllinux_1_2_aarch64.whl", hash = "sha256:fd86572566fb40189a8260446158235159bc7a82dfbc87a3b39cf4fb57fcec1c"}, - {file = "coverage-7.14.1-cp314-cp314-musllinux_1_2_i686.whl", hash = "sha256:7771b601718fdde84832c3a434ca9bbf4ae9adbc49d84198b4110700c3c77c36"}, - {file = "coverage-7.14.1-cp314-cp314-musllinux_1_2_ppc64le.whl", hash = "sha256:39b21e212c55af06fa375e3dbf90a8a8e38792f3a910c580066d23563830ddd5"}, - {file = "coverage-7.14.1-cp314-cp314-musllinux_1_2_riscv64.whl", hash = "sha256:f2302660e32562a532b442480121aef8aa61a5bdb20b30bf0adab29f10a5a4b4"}, - {file = "coverage-7.14.1-cp314-cp314-musllinux_1_2_x86_64.whl", hash = "sha256:03a6f93c1ec3b7f2e77b5dbcc5573a2c21f12529a5c6bbe0f16f72303cc2fa4d"}, - {file = "coverage-7.14.1-cp314-cp314-win32.whl", hash = "sha256:8a3ce026d73290f42f08dafecbd82c193a74df280461fbf97300fec51fd133ee"}, - {file = "coverage-7.14.1-cp314-cp314-win_amd64.whl", hash = "sha256:114c95ef29302423b87d159075805f4ab973254a2638a5d7d046c94887cc87d7"}, - {file = "coverage-7.14.1-cp314-cp314-win_arm64.whl", hash = "sha256:a07891c3f4805442b31b71e84ba3cf29ed1aa9a428284e06deeb4b23e5b46343"}, - {file = "coverage-7.14.1-cp314-cp314t-macosx_10_15_x86_64.whl", hash = "sha256:1101a5ebb083aecb625ebb6209d4105b58f647b093cb2dc8122d7b33f743cfe1"}, - {file = "coverage-7.14.1-cp314-cp314t-macosx_11_0_arm64.whl", hash = "sha256:851b9e1e4e8a4608e77c79714b2e77c0970d2ed7202a05e92ae407817481887b"}, - {file = "coverage-7.14.1-cp314-cp314t-manylinux1_i686.manylinux_2_28_i686.manylinux_2_5_i686.whl", hash = "sha256:d5b89cdfb2ee051b71e8c3c70bd81a9eff81100f736a269136fe1a68efe00474"}, - {file = "coverage-7.14.1-cp314-cp314t-manylinux1_x86_64.manylinux_2_28_x86_64.manylinux_2_5_x86_64.whl", hash = "sha256:0177614a0370f227888b4e436a7c55686d6a9f90eb1ade2b624ba685a1686e86"}, - {file = "coverage-7.14.1-cp314-cp314t-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:2d69af5dea2de76fc485a83032a630523f985198b7e25be901ec60181587b01e"}, - {file = "coverage-7.14.1-cp314-cp314t-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:35ab22d91de736e8966b980dc355cbcdd2c6dbbcfe275f9a2991bc8a91b3df65"}, - {file = "coverage-7.14.1-cp314-cp314t-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:357d4e32935c36588aaba057d734fa32428c360c9fc2e4442afbf1b646beee6e"}, - {file = "coverage-7.14.1-cp314-cp314t-musllinux_1_2_aarch64.whl", hash = "sha256:51bd64741cc6fa065abd300ede1afe5a5291ece9c31da8b24884deda48bcc3f8"}, - {file = "coverage-7.14.1-cp314-cp314t-musllinux_1_2_i686.whl", hash = "sha256:9132cd363a68a4c3daa7c8704a654b1e39d3360f6f5b8ddd470608a945236c07"}, - {file = "coverage-7.14.1-cp314-cp314t-musllinux_1_2_ppc64le.whl", hash = "sha256:07c6290b1697b862c0478eab545eec949a0d0e4d6d03497f446d706da3b4f2de"}, - {file = "coverage-7.14.1-cp314-cp314t-musllinux_1_2_riscv64.whl", hash = "sha256:5ea0c297e27133853b4d8a3eb799bff5a2dbd9f2f41537a240d337ac9b4df890"}, - {file = "coverage-7.14.1-cp314-cp314t-musllinux_1_2_x86_64.whl", hash = "sha256:01b7733daad0237daa01ef80fe2dfceffc911e6a17fa7b55d14aa8214eaaaecd"}, - {file = "coverage-7.14.1-cp314-cp314t-win32.whl", hash = "sha256:6adc5a36984624a70bf11d7184e20fa0a49aa7c47ffab43804106a1a695ea22e"}, - {file = "coverage-7.14.1-cp314-cp314t-win_amd64.whl", hash = "sha256:ddf799247318f34dbcd2efa8c95a8d0642674e926bb1774cf9b63dfd2a389d1c"}, - {file = "coverage-7.14.1-cp314-cp314t-win_arm64.whl", hash = "sha256:145986fe66647eb489f18d9a997567a3fd358584c4b5a808769113abc07466af"}, - {file = "coverage-7.14.1-py3-none-any.whl", hash = "sha256:a252f21c27e38347e60111a3266b03827422a7d5525951aceee313aa68bab1d2"}, - {file = "coverage-7.14.1.tar.gz", hash = "sha256:30c08f7d90415aa98b3c990385dea2939b0da55f38515e5b369b83655f8523be"}, + {file = "coverage-7.14.3-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:360bec1f58e7243e3405d3bdf7a1a8115aa9b448d54dc7cd6f7b7e0e9406b62e"}, + {file = "coverage-7.14.3-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:ed68faa5e85de2f3e400bc3f122e5c82735a58c8bb24b9f63a2215954ba17b2d"}, + {file = "coverage-7.14.3-cp310-cp310-manylinux1_i686.manylinux_2_28_i686.manylinux_2_5_i686.whl", hash = "sha256:830c1fca669c572dec37ce9c838224ee45aac5be0f6961edf871e82e49d6537c"}, + {file = "coverage-7.14.3-cp310-cp310-manylinux1_x86_64.manylinux_2_28_x86_64.manylinux_2_5_x86_64.whl", hash = "sha256:a64caee2193563601dbaaa55fe2dcf597debef04a2f8f1fa8a07aa4bb7ac7a1e"}, + {file = "coverage-7.14.3-cp310-cp310-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:0096fd7559178f0cc9cf088f2dbd2a02ef85bacaa69732c633517286b4494610"}, + {file = "coverage-7.14.3-cp310-cp310-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:6197e5a00183c11a8ce7c6abd18be1a9189fd8399084ffc95196f4f0db4f2137"}, + {file = "coverage-7.14.3-cp310-cp310-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:7dfe427045520d6abca33687dfef767b4f635015893a1816c5decb12eb72ce18"}, + {file = "coverage-7.14.3-cp310-cp310-musllinux_1_2_aarch64.whl", hash = "sha256:9a3f142070eb7b82fc4085a55d887396f9c4e21250bccebe2ba22502c45b9647"}, + {file = "coverage-7.14.3-cp310-cp310-musllinux_1_2_i686.whl", hash = "sha256:64b2055bb6e0dc945af35cdeceb3633e6ed9273475ef3af85592410fd6803803"}, + {file = "coverage-7.14.3-cp310-cp310-musllinux_1_2_ppc64le.whl", hash = "sha256:1551b4caac3e3ec9f2bfcec6bf3776e01c0edbdd2e240431a50ca1a1aac72c27"}, + {file = "coverage-7.14.3-cp310-cp310-musllinux_1_2_riscv64.whl", hash = "sha256:583d50d59142f8549470bd6390471d0fe8b8c8d69d6a0f28ac71e05380cef640"}, + {file = "coverage-7.14.3-cp310-cp310-musllinux_1_2_x86_64.whl", hash = "sha256:e0bb8a6bc7015efdf8a928753b25da1b9ca2d6f24ef04d2ee0688e486f32aae7"}, + {file = "coverage-7.14.3-cp310-cp310-win32.whl", hash = "sha256:d48400185564042287dc487c1f016a3397f18ab4f4c5d5ec36edc218f7ffa35b"}, + {file = "coverage-7.14.3-cp310-cp310-win_amd64.whl", hash = "sha256:eadea7aba74e40adee867a8c0eec17b820b061d308a4b014f7a0e118c2b0aa61"}, + {file = "coverage-7.14.3-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:e574801e1d643561594aa021206c46d80b257e9853087090ba97bed8b0a509d3"}, + {file = "coverage-7.14.3-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:f82b6bb7d75a2613e85d07cefa3a8c973d0544a8993337f6e2728e4a1e94c305"}, + {file = "coverage-7.14.3-cp311-cp311-manylinux1_i686.manylinux_2_28_i686.manylinux_2_5_i686.whl", hash = "sha256:a2335ea5fed26af2e831094964fa3f8fae60b45f7e37fcc2d3b615b2add3ad87"}, + {file = "coverage-7.14.3-cp311-cp311-manylinux1_x86_64.manylinux_2_28_x86_64.manylinux_2_5_x86_64.whl", hash = "sha256:fbb8c3a98e779013786ae01d229662aeacbc77100efbd3f2f245219ace5af700"}, + {file = "coverage-7.14.3-cp311-cp311-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:ac082660de8f429ba0ea363595abb838998570b9a7546777c60f413ab902bbde"}, + {file = "coverage-7.14.3-cp311-cp311-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:8ac012839ff7e396030f1e94e10553a431d14e4de2ab65cb3acb72bbd5628ca2"}, + {file = "coverage-7.14.3-cp311-cp311-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:5952f8c1bda2a5347154450379316e6dfa4d934d62ca35f6784451e6f55074fb"}, + {file = "coverage-7.14.3-cp311-cp311-musllinux_1_2_aarch64.whl", hash = "sha256:8cf0f2509acb4619e2471a1951089054dd58ebea7a912066d2ea56dd4c24ca4a"}, + {file = "coverage-7.14.3-cp311-cp311-musllinux_1_2_i686.whl", hash = "sha256:2e41fd3aab806770008279a93879b0924b16247e09ab537c043d08bbca53b4ab"}, + {file = "coverage-7.14.3-cp311-cp311-musllinux_1_2_ppc64le.whl", hash = "sha256:f0a47095963cfe054e0df178daca95aec21e680d6076da807c3add28dfe920f7"}, + {file = "coverage-7.14.3-cp311-cp311-musllinux_1_2_riscv64.whl", hash = "sha256:a090cbf9521e78ffdb2fcf448b72902afe9f5923ff6a12d5c0d0120200348af9"}, + {file = "coverage-7.14.3-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:4d310baf69a4fbe8a098ce727e4808a34866ac718a6f759ae659cbd3221358bc"}, + {file = "coverage-7.14.3-cp311-cp311-win32.whl", hash = "sha256:74fdd718d88fe144f4579b8747873a07ec3f04cb837d5faec5a25d9e22fa31a8"}, + {file = "coverage-7.14.3-cp311-cp311-win_amd64.whl", hash = "sha256:cc96aa922e21d4bc5d5ed3c915cef27dfcbc13686f47d5e378d647fbfba655a2"}, + {file = "coverage-7.14.3-cp311-cp311-win_arm64.whl", hash = "sha256:c66f9f9d4f1e9712eb9b1de5310f881d4e2188cfcba5065e1a8490f38687f2c4"}, + {file = "coverage-7.14.3-cp312-cp312-macosx_10_13_x86_64.whl", hash = "sha256:3d74ff26299c4879ce3a4d826f9d3d4d556fd285fde7bbce3c0ef5a8ab1cec24"}, + {file = "coverage-7.14.3-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:96150a9cf3468ea20f0bc5d0e21b3df8972c31480ef90fa7614b773cc6429665"}, + {file = "coverage-7.14.3-cp312-cp312-manylinux1_i686.manylinux_2_28_i686.manylinux_2_5_i686.whl", hash = "sha256:27d07a46500ba23515b838dbcf52512026af04090755cf6cc64166d88c9b9a1a"}, + {file = "coverage-7.14.3-cp312-cp312-manylinux1_x86_64.manylinux_2_28_x86_64.manylinux_2_5_x86_64.whl", hash = "sha256:621e13c6108234d7960aaf5762ab5c3c00f33c30c15af06dcbff0c73bf112727"}, + {file = "coverage-7.14.3-cp312-cp312-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:4b60ca6d8af70473491a15a343cbabab2e8f9ea66a4376e81c7aa24876a6f977"}, + {file = "coverage-7.14.3-cp312-cp312-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:c90a7cdd5e380e1ce02f19792e2ac2fbfbf177e35a27e69fd3e873b30d895c0c"}, + {file = "coverage-7.14.3-cp312-cp312-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:5d788e5fd55347eef06ca0732c77d04a264de67e8ff24631270cdff3767a60cf"}, + {file = "coverage-7.14.3-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:62c7f79db2851c95ef020e5d28b97afde3daf9f7febcd35b53e05638f729063f"}, + {file = "coverage-7.14.3-cp312-cp312-musllinux_1_2_i686.whl", hash = "sha256:90f7608aeb5d9b60b523b9fb2a4ee1973867cc4865a3f26fe6c7577073b70205"}, + {file = "coverage-7.14.3-cp312-cp312-musllinux_1_2_ppc64le.whl", hash = "sha256:1e3b91f9c4740aeb571ecf82e5e8d8e4ab62d34fcb5a5d4e5baa38c6f7d2857c"}, + {file = "coverage-7.14.3-cp312-cp312-musllinux_1_2_riscv64.whl", hash = "sha256:c946099774a7699de03cbd0ff0a64e21aed4525eed9d959adde4afe6d15758ef"}, + {file = "coverage-7.14.3-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:16b206e521feb8b7133a45754643dead0538489cf8b783b90cf5f4e3299625fd"}, + {file = "coverage-7.14.3-cp312-cp312-win32.whl", hash = "sha256:ea3169c7116eb6cdf7608c6c7da9ecfcb3da40688e3a510fac2d1d2bafd6dc35"}, + {file = "coverage-7.14.3-cp312-cp312-win_amd64.whl", hash = "sha256:7ea52fc08f007bcc494d4bb3df3851e95843d881860ba38fe2c64dc100db5e7d"}, + {file = "coverage-7.14.3-cp312-cp312-win_arm64.whl", hash = "sha256:8cec0ad652ec57790970d817490105bd917d783c2f7b38d6b58a0ca312e1a336"}, + {file = "coverage-7.14.3-cp313-cp313-macosx_10_13_x86_64.whl", hash = "sha256:47968988b367990ae4ab17523790c38cd125e02c6bfd379b6022be2d40bdc38c"}, + {file = "coverage-7.14.3-cp313-cp313-macosx_11_0_arm64.whl", hash = "sha256:0ee68f5c34812780f3a7063382c0a9fcbb99985b7ddcdcaa626e4f3fb2e0783a"}, + {file = "coverage-7.14.3-cp313-cp313-manylinux1_i686.manylinux_2_28_i686.manylinux_2_5_i686.whl", hash = "sha256:fa9e5c6857a7e80fa22ace5cf3550ae392bbfc322f1d8dd2d2d5a8be38cec027"}, + {file = "coverage-7.14.3-cp313-cp313-manylinux1_x86_64.manylinux_2_28_x86_64.manylinux_2_5_x86_64.whl", hash = "sha256:98a0859b0e98e43e1178a9402e19c8127766b14f7109a374d976e5a62c0e5c73"}, + {file = "coverage-7.14.3-cp313-cp313-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:69918344541ed9c8368566c2adc03c0e33d4550d7faa87d1b35e49b6a3286ea9"}, + {file = "coverage-7.14.3-cp313-cp313-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:b7f300ac92cd4b570724c8ffbbd0c130fee298d2447f41d5a3abf58976fae1de"}, + {file = "coverage-7.14.3-cp313-cp313-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:11a7ec9f97ab950f4c5af62229befc7faf208fdbc0116d3902d7e306cf2c5abd"}, + {file = "coverage-7.14.3-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:a571bd889cd36c5922ce8e42e059f9d37d02301531d11374afa4c87a578625d5"}, + {file = "coverage-7.14.3-cp313-cp313-musllinux_1_2_i686.whl", hash = "sha256:de76caefc8deabb0dd1678b6a980be97d14c8d87e213ac194dbf8b09e96d63fb"}, + {file = "coverage-7.14.3-cp313-cp313-musllinux_1_2_ppc64le.whl", hash = "sha256:d20a15c622194234161535459affa8f7905830391c9ccfa060d495dbfe3a1c7f"}, + {file = "coverage-7.14.3-cp313-cp313-musllinux_1_2_riscv64.whl", hash = "sha256:b488bd4b23397db62e7a9459129d01ff06a846582a732efd24834b24a6ada498"}, + {file = "coverage-7.14.3-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:6a3693b4153394d265f44fb855fdc80e72403024d4d6f91c4871b334d028e4e0"}, + {file = "coverage-7.14.3-cp313-cp313-win32.whl", hash = "sha256:338b19131ab1a6b767b462bfcbaa692e7ae22f24463e39d49b02a83410ff6b37"}, + {file = "coverage-7.14.3-cp313-cp313-win_amd64.whl", hash = "sha256:b3d77f7f196abdef7e01415de1bce09f216189e83e58159cfeef2b92d0464994"}, + {file = "coverage-7.14.3-cp313-cp313-win_arm64.whl", hash = "sha256:e6230e688c7c3e65cedd41a774eb4ec221adc6bfee13768231015b702d5e4150"}, + {file = "coverage-7.14.3-cp314-cp314-macosx_10_15_x86_64.whl", hash = "sha256:605ab2b566a22bd94834529d66d295c364aba84afd3e5498285c7a524017b1fc"}, + {file = "coverage-7.14.3-cp314-cp314-macosx_11_0_arm64.whl", hash = "sha256:a3c2134809e80fac091bfed18a6991b5a5eb5df5ae32b17ac4f4f99864b73dd7"}, + {file = "coverage-7.14.3-cp314-cp314-manylinux1_i686.manylinux_2_28_i686.manylinux_2_5_i686.whl", hash = "sha256:c02efd507227bde9969cab0db8f48890eb3b5dcad6afac57a4792df4133543ce"}, + {file = "coverage-7.14.3-cp314-cp314-manylinux1_x86_64.manylinux_2_28_x86_64.manylinux_2_5_x86_64.whl", hash = "sha256:1bb93c2aa61d2a5b38f1526546d95cf4132cb681e541a337bf8dfd092be816e5"}, + {file = "coverage-7.14.3-cp314-cp314-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:f502e948e03e866538048bba081c075caaa62e5bda6ea5b7432e45f587eb462a"}, + {file = "coverage-7.14.3-cp314-cp314-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:9973ef2463f8e6cfb61a6324126bb3e17d67a85f22f58d856e583ea2e3ca6501"}, + {file = "coverage-7.14.3-cp314-cp314-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:9be4e7d4c5ca0427889f8f9d614bd630c2be741b1de7699bca3b2b6c0e41003e"}, + {file = "coverage-7.14.3-cp314-cp314-musllinux_1_2_aarch64.whl", hash = "sha256:a574912f3bde4b0619f6e97d01aa590b70998859244793769eb3a6df78ee56d3"}, + {file = "coverage-7.14.3-cp314-cp314-musllinux_1_2_i686.whl", hash = "sha256:e343fb086c9cd780b38622fea7c369acd64c1a0724312149b5d769c387a2b1f5"}, + {file = "coverage-7.14.3-cp314-cp314-musllinux_1_2_ppc64le.whl", hash = "sha256:3c68df8e61f1e09633fefc7538297145623957a048534368c9d212782aa5e845"}, + {file = "coverage-7.14.3-cp314-cp314-musllinux_1_2_riscv64.whl", hash = "sha256:3e5b550a128419373c2f6cec28a244207013ef15f5cbcff6a5ca09d1dfaaf027"}, + {file = "coverage-7.14.3-cp314-cp314-musllinux_1_2_x86_64.whl", hash = "sha256:2bfc4dd0a912329eccc7484a7d0b2a38032b38c40663b1e1ac595f10c457954b"}, + {file = "coverage-7.14.3-cp314-cp314-win32.whl", hash = "sha256:0423d64c013057a06e70f070f073cec4b0cbc7d2b27f3c7007292f2ff1d52965"}, + {file = "coverage-7.14.3-cp314-cp314-win_amd64.whl", hash = "sha256:92c22e19ce64ca3f2ad751f16f14df1468b4c231bd6af97185063a9c292a0cb3"}, + {file = "coverage-7.14.3-cp314-cp314-win_arm64.whl", hash = "sha256:41de778bd41780586e2b04912079c73089ab5d839624e28db3bdb26de638da92"}, + {file = "coverage-7.14.3-cp314-cp314t-macosx_10_15_x86_64.whl", hash = "sha256:8427f370ca67db4c975d2a26acfc0e5783ca0b52444dbc50278ace0f35445949"}, + {file = "coverage-7.14.3-cp314-cp314t-macosx_11_0_arm64.whl", hash = "sha256:d8e88f335544a47e22ae2e45b344772925ec65166555c958720d5ed971880891"}, + {file = "coverage-7.14.3-cp314-cp314t-manylinux1_i686.manylinux_2_28_i686.manylinux_2_5_i686.whl", hash = "sha256:beaab199b9e5ceaf5a225e16a9d4df136f2a1eae0a5c20de1e277c8a5225f388"}, + {file = "coverage-7.14.3-cp314-cp314t-manylinux1_x86_64.manylinux_2_28_x86_64.manylinux_2_5_x86_64.whl", hash = "sha256:b3ff255799f5a1676c71c1c32ec01fd043aa09d57b3d95764b24992757184784"}, + {file = "coverage-7.14.3-cp314-cp314t-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:878832eaac515b62decfa76965aed558775f86bf1fc8cca76993c0c84ae31aed"}, + {file = "coverage-7.14.3-cp314-cp314t-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:611e62cb9386096d81b63e0a05330750268617231e7bd598e1fe77482a2c58a5"}, + {file = "coverage-7.14.3-cp314-cp314t-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:02c41de2a88011b893050fc9830267d927a50a215f7ad5ec17349db7090ccf26"}, + {file = "coverage-7.14.3-cp314-cp314t-musllinux_1_2_aarch64.whl", hash = "sha256:526ce9721116af23b1065089f0b75046fe521e7772ab94b641cd66b7a0421889"}, + {file = "coverage-7.14.3-cp314-cp314t-musllinux_1_2_i686.whl", hash = "sha256:e4ed44705ca4bead6fc977a8b741f2145608289b33c8a9b42a95d0f15aedbf4d"}, + {file = "coverage-7.14.3-cp314-cp314t-musllinux_1_2_ppc64le.whl", hash = "sha256:2415902f385a23dcc4ccd26e0ba803249a169af6a930c003a4c715eeb9a5444e"}, + {file = "coverage-7.14.3-cp314-cp314t-musllinux_1_2_riscv64.whl", hash = "sha256:b75ee850fc2d7c831e883220c445b035f2224de2ba6103f1e56dbd237ab913f7"}, + {file = "coverage-7.14.3-cp314-cp314t-musllinux_1_2_x86_64.whl", hash = "sha256:dc9b4e35e7c3920e925ba7f14886fd5fbe481232754624e832ddba66c7535635"}, + {file = "coverage-7.14.3-cp314-cp314t-win32.whl", hash = "sha256:7b27c822a8161afbe48e99f1adfb098d270ae7e0f7d7b0555ce110529bdb69cc"}, + {file = "coverage-7.14.3-cp314-cp314t-win_amd64.whl", hash = "sha256:39e1dbbb6ff2c338e0196a482558a792a1de3aa64261196f5cdb3da016ad9cda"}, + {file = "coverage-7.14.3-cp314-cp314t-win_arm64.whl", hash = "sha256:68520c90babfa2d560eca6d497921ed3a4f469623bd709733124491b2aa8ef3f"}, + {file = "coverage-7.14.3-py3-none-any.whl", hash = "sha256:fb7e18afb6e903c1a92401a2f0501ac277dca527bb9ca6fe1f691a8a0026a0e8"}, + {file = "coverage-7.14.3.tar.gz", hash = "sha256:1a7563a443f3d53fdeb040ec8c9f7466aed7ca3dc5891aa09d3ca3625fa4387f"}, ] [package.dependencies] tomli = {version = "*", optional = true, markers = "python_full_version <= \"3.11.0a6\" and extra == \"toml\""} [package.extras] -toml = ["tomli"] +toml = ["tomli ; python_full_version <= \"3.11.0a6\""] [[package]] name = "defusedxml" @@ -287,6 +277,7 @@ version = "0.7.1" description = "XML bomb protection for Python stdlib modules" optional = false python-versions = ">=2.7, !=3.0.*, !=3.1.*, !=3.2.*, !=3.3.*, !=3.4.*" +groups = ["main"] files = [ {file = "defusedxml-0.7.1-py2.py3-none-any.whl", hash = "sha256:a352e7e428770286cc899e2542b6cdaedb2b4953ff269a210103ec58f6198a61"}, {file = "defusedxml-0.7.1.tar.gz", hash = "sha256:1bb3032db185915b62d7c6209c5a8792be6a32ab2fedacc84e01b52c51aa3e69"}, @@ -298,6 +289,7 @@ version = "5.0" description = "A library for working with .desktop files" optional = false python-versions = ">=3.10" +groups = ["dev"] files = [ {file = "desktop_entry_lib-5.0-py3-none-any.whl", hash = "sha256:e60a0c2c5e42492dbe5378e596b1de87d1b1c4dc74d1f41998a164ee27a1226f"}, {file = "desktop_entry_lib-5.0.tar.gz", hash = "sha256:9a621bac1819fe21021356e41fec0ac096ed56e6eb5dcfe0639cd8654914b864"}, @@ -312,6 +304,8 @@ version = "1.3.1" description = "Backport of PEP 654 (exception groups)" optional = false python-versions = ">=3.7" +groups = ["dev"] +markers = "python_version == \"3.10\"" files = [ {file = "exceptiongroup-1.3.1-py3-none-any.whl", hash = "sha256:a7a39a3bd276781e98394987d3a5701d0c4edffb633bb7a5144577f82c773598"}, {file = "exceptiongroup-1.3.1.tar.gz", hash = "sha256:8b412432c6055b0b7d14c310000ae93352ed6754f70fa8f7c34141f91c4e3219"}, @@ -329,6 +323,7 @@ version = "3.18" description = "Internationalized Domain Names in Applications (IDNA)" optional = false python-versions = ">=3.9" +groups = ["dev"] files = [ {file = "idna-3.18-py3-none-any.whl", hash = "sha256:7f952cbe720b688055e3f87de14f5c3e5fdaa8bc3928985c4077ca689de849a2"}, {file = "idna-3.18.tar.gz", hash = "sha256:ffb385a7e039654cef1ab9ef32c6fafe283c0c0467bba1d9029738ce4a14a848"}, @@ -343,6 +338,7 @@ version = "2.3.0" description = "brain-dead simple config-ini parsing" optional = false python-versions = ">=3.10" +groups = ["dev"] files = [ {file = "iniconfig-2.3.0-py3-none-any.whl", hash = "sha256:f631c04d2c48c52b84d0d0549c99ff3859c98df65b3101406327ecc7d53fbf12"}, {file = "iniconfig-2.3.0.tar.gz", hash = "sha256:c76315c77db068650d49c5b56314774a7804df16fee4402c1f19d6d15d8c4730"}, @@ -354,6 +350,7 @@ version = "3.1.6" description = "A very fast and expressive template engine." optional = false python-versions = ">=3.7" +groups = ["main"] files = [ {file = "jinja2-3.1.6-py3-none-any.whl", hash = "sha256:85ece4451f492d0c13c5dd7c13a64681a86afae63a5f347908daf103ce6d2f67"}, {file = "jinja2-3.1.6.tar.gz", hash = "sha256:0137fb05990d35f1275a587e9aee6d56da821fc83491a0fb838183be43f66d6d"}, @@ -371,6 +368,7 @@ version = "3.0.3" description = "Safely add untrusted strings to HTML/XML markup." optional = false python-versions = ">=3.9" +groups = ["main"] files = [ {file = "markupsafe-3.0.3-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:2f981d352f04553a7171b8e44369f2af4055f888dfb147d55e42d29e29e74559"}, {file = "markupsafe-3.0.3-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:e1c1493fb6e50ab01d20a22826e57520f1284df32f2d8601fdd90b6304601419"}, @@ -469,6 +467,7 @@ version = "26.2" description = "Core utilities for Python packages" optional = false python-versions = ">=3.8" +groups = ["dev"] files = [ {file = "packaging-26.2-py3-none-any.whl", hash = "sha256:5fc45236b9446107ff2415ce77c807cee2862cb6fac22b8a73826d0693b0980e"}, {file = "packaging-26.2.tar.gz", hash = "sha256:ff452ff5a3e828ce110190feff1178bb1f2ea2281fa2075aadb987c2fb221661"}, @@ -480,6 +479,7 @@ version = "1.6.0" description = "plugin and hook calling mechanisms for python" optional = false python-versions = ">=3.9" +groups = ["dev"] files = [ {file = "pluggy-1.6.0-py3-none-any.whl", hash = "sha256:e920276dd6813095e9377c0bc5566d94c932c33b27a3e3945d8389c374dd4746"}, {file = "pluggy-1.6.0.tar.gz", hash = "sha256:7dcc130b76258d33b90f61b658791dede3486c3e6bfb003ee5c9bfb396dd22f3"}, @@ -495,6 +495,7 @@ version = "2.20.0" description = "Pygments is a syntax highlighting package written in Python." optional = false python-versions = ">=3.9" +groups = ["dev"] files = [ {file = "pygments-2.20.0-py3-none-any.whl", hash = "sha256:81a9e26dd42fd28a23a2d169d86d7ac03b46e2f8b59ed4698fb4785f946d0176"}, {file = "pygments-2.20.0.tar.gz", hash = "sha256:6757cd03768053ff99f3039c1a36d6c0aa0b263438fcab17520b30a303a82b5f"}, @@ -509,6 +510,7 @@ version = "4.2" description = "Generate AppImages from your Python projects" optional = false python-versions = ">=3.9" +groups = ["dev"] files = [ {file = "pyproject_appimage-4.2-py3-none-any.whl", hash = "sha256:d6892643db5759dc06531a4546bdab404a519c63814c060f8749979a8625d9cc"}, {file = "pyproject_appimage-4.2.tar.gz", hash = "sha256:6b6387250cb1e6ecbb08a13f5810749396ebe8637f2f35bf2296bfdd5e65cd6e"}, @@ -525,6 +527,7 @@ version = "8.4.2" description = "pytest: simple powerful testing with Python" optional = false python-versions = ">=3.9" +groups = ["dev"] files = [ {file = "pytest-8.4.2-py3-none-any.whl", hash = "sha256:872f880de3fc3a5bdc88a11b39c9710c3497a547cfa9320bc3c5e62fbf272e79"}, {file = "pytest-8.4.2.tar.gz", hash = "sha256:86c0d0b93306b961d58d62a4db4879f27fe25513d4b969df351abdddb3c30e01"}, @@ -548,6 +551,7 @@ version = "5.0.0" description = "Pytest plugin for measuring coverage." optional = false python-versions = ">=3.8" +groups = ["dev"] files = [ {file = "pytest-cov-5.0.0.tar.gz", hash = "sha256:5837b58e9f6ebd335b0f8060eecce69b662415b16dc503883a02f45dfeb14857"}, {file = "pytest_cov-5.0.0-py3-none-any.whl", hash = "sha256:4f0764a1219df53214206bf1feea4633c3b558a2925c8b59f144f682861ce652"}, @@ -566,6 +570,7 @@ version = "6.0.3" description = "YAML parser and emitter for Python" optional = false python-versions = ">=3.8" +groups = ["main"] files = [ {file = "PyYAML-6.0.3-cp38-cp38-macosx_10_13_x86_64.whl", hash = "sha256:c2514fceb77bc5e7a2f7adfaa1feb2fb311607c9cb518dbc378688ec73d8292f"}, {file = "PyYAML-6.0.3-cp38-cp38-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:9c57bb8c96f6d1808c030b1687b9b5fb476abaa47f0db9c0101f5e9f394e97f4"}, @@ -648,6 +653,7 @@ version = "2.34.2" description = "Python HTTP for Humans." optional = false python-versions = ">=3.10" +groups = ["dev"] files = [ {file = "requests-2.34.2-py3-none-any.whl", hash = "sha256:2a0d60c172f83ac6ab31e4554906c0f3b3588d37b5cb939b1c061f4907e278e0"}, {file = "requests-2.34.2.tar.gz", hash = "sha256:f288924cae4e29463698d6d60bc6a4da69c89185ad1e0bcc4104f584e960b9ed"}, @@ -669,6 +675,7 @@ version = "2.4.1" description = "A lil' TOML parser" optional = false python-versions = ">=3.8" +groups = ["main", "dev"] files = [ {file = "tomli-2.4.1-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:f8f0fc26ec2cc2b965b7a3b87cd19c5c6b8c5e5f436b984e85f486d652285c30"}, {file = "tomli-2.4.1-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:4ab97e64ccda8756376892c53a72bd1f964e519c77236368527f758fbc36a53a"}, @@ -718,6 +725,7 @@ files = [ {file = "tomli-2.4.1-py3-none-any.whl", hash = "sha256:0d85819802132122da43cb86656f8d1f8c6587d54ae7dcaf30e90533028b49fe"}, {file = "tomli-2.4.1.tar.gz", hash = "sha256:7c7e1a961a0b2f2472c1ac5b69affa0ae1132c39adcb67aba98568702b9cc23f"}, ] +markers = {main = "python_version == \"3.10\"", dev = "python_full_version <= \"3.11.0a6\""} [[package]] name = "typing-extensions" @@ -725,6 +733,8 @@ version = "4.15.0" description = "Backported and Experimental Type Hints for Python 3.9+" optional = false python-versions = ">=3.9" +groups = ["dev"] +markers = "python_version == \"3.10\"" files = [ {file = "typing_extensions-4.15.0-py3-none-any.whl", hash = "sha256:f0fa19c6845758ab08074a0cfa8b7aecb71c999ca73d62883bc25cc018c4e548"}, {file = "typing_extensions-4.15.0.tar.gz", hash = "sha256:0cea48d173cc12fa28ecabc3b837ea3cf6f38c6d1136f85cbaaf598984861466"}, @@ -736,18 +746,19 @@ version = "2.7.0" description = "HTTP library with thread-safe connection pooling, file post, and more." optional = false python-versions = ">=3.10" +groups = ["dev"] files = [ {file = "urllib3-2.7.0-py3-none-any.whl", hash = "sha256:9fb4c81ebbb1ce9531cce37674bbc6f1360472bc18ca9a553ede278ef7276897"}, {file = "urllib3-2.7.0.tar.gz", hash = "sha256:231e0ec3b63ceb14667c67be60f2f2c40a518cb38b03af60abc813da26505f4c"}, ] [package.extras] -brotli = ["brotli (>=1.2.0)", "brotlicffi (>=1.2.0.0)"] +brotli = ["brotli (>=1.2.0) ; platform_python_implementation == \"CPython\"", "brotlicffi (>=1.2.0.0) ; platform_python_implementation != \"CPython\""] h2 = ["h2 (>=4,<5)"] socks = ["pysocks (>=1.5.6,!=1.5.7,<2.0)"] -zstd = ["backports-zstd (>=1.0.0)"] +zstd = ["backports-zstd (>=1.0.0) ; python_version < \"3.14\""] [metadata] -lock-version = "2.0" -python-versions = "^3.10" -content-hash = "026c4acd254e889b70bb8c25ffb5e6323eee86380f54f2d8ef02f59ae9307529" +lock-version = "2.1" +python-versions = ">=3.10,<4.0" +content-hash = "161dfd9b44e1063656bacea8e8fb08a2614361a8262d8f665240e4f391732e1b" diff --git a/pyproject.toml b/pyproject.toml index cbc30c8..108a7b2 100644 --- a/pyproject.toml +++ b/pyproject.toml @@ -1,36 +1,40 @@ -[tool.poetry] +[project] name = "jinjaturtle" version = "0.5.5" description = "Convert config files into Ansible defaults and Jinja2 templates." -authors = ["Miguel Jacq "] +authors = [ + { name = "Miguel Jacq", email = "mig@mig5.net" }, +] license = "GPL-3.0-or-later" readme = "README.md" -packages = [{ include = "jinjaturtle", from = "src" }] - +requires-python = ">=3.10,<4.0" keywords = ["ansible", "jinja2", "config", "toml", "ini", "yaml", "json", "devops"] +dependencies = [ + "PyYAML (>=6.0,<7.0)", + "defusedxml (>=0.7.1,<0.8.0)", + "jinja2 (>=3.1.6,<4.0.0)", + "tomli (>=2.0.0,<3.0.0) ; python_version < '3.11'", +] +[project.urls] homepage = "https://git.mig5.net/mig5/jinjaturtle" repository = "https://git.mig5.net/mig5/jinjaturtle" -[tool.poetry.dependencies] -python = "^3.10" -PyYAML = "^6.0" -tomli = { version = "^2.0.0", python = "<3.11" } -defusedxml = "^0.7.1" -jinja2 = "^3.1.6" - -[tool.poetry.scripts] +[project.scripts] jinjaturtle = "jinjaturtle.cli:main" +[tool.poetry] +packages = [{ include = "jinjaturtle", from = "src" }] + +[tool.poetry.group.dev.dependencies] +pytest = "^8" +pytest-cov = "^5" +pyproject-appimage = "^4.2" + [build-system] -requires = ["poetry-core>=1.0.0"] +requires = ["poetry-core>=2.0.0"] build-backend = "poetry.core.masonry.api" [tool.pyproject-appimage] script = "jinjaturtle" output = "JinjaTurtle.AppImage" - -[tool.poetry.dev-dependencies] -pytest = "^8" -pytest-cov = "^5" -pyproject-appimage = "^4.2" From a5f8e7c481dbbb108c4b4be4efd76281359f25a7 Mon Sep 17 00:00:00 2001 From: Miguel Jacq Date: Tue, 23 Jun 2026 15:42:42 +1000 Subject: [PATCH 06/25] Attempt to fix python bin --- .forgejo/workflows/ci.yml | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/.forgejo/workflows/ci.yml b/.forgejo/workflows/ci.yml index 0773dbb..67c69d3 100644 --- a/.forgejo/workflows/ci.yml +++ b/.forgejo/workflows/ci.yml @@ -7,6 +7,14 @@ jobs: test: runs-on: docker + strategy: + fail-fast: false + matrix: + include: + - distro: debian + image: docker.io/library/debian:13 + python: python3 + steps: - name: Checkout uses: actions/checkout@v4 From 383a529016da534ea8927c4af34a4cb751388226 Mon Sep 17 00:00:00 2001 From: Miguel Jacq Date: Tue, 23 Jun 2026 15:57:17 +1000 Subject: [PATCH 07/25] fix test --- tests/test_injection_security.py | 28 ++++++++++++++++++++++++++-- 1 file changed, 26 insertions(+), 2 deletions(-) diff --git a/tests/test_injection_security.py b/tests/test_injection_security.py index 642c0b8..75edc70 100644 --- a/tests/test_injection_security.py +++ b/tests/test_injection_security.py @@ -23,8 +23,11 @@ import jinja2 import pytest import yaml as pyyaml -from jinjaturtle.escape import escape_jinja_literal, escape_erb_literal - +from jinjaturtle.escape import ( + escape_jinja_literal, + escape_erb_literal, + escape_literal, +) TRIP = "__TRIPWIRE_FIRED__" @@ -210,3 +213,24 @@ def test_escape_erb_literal_removes_executable_tags(payload): assert "system" not in chunk assert "require" not in chunk # Numeric/expression payloads must be reduced to literal-string prints. + + +def test_escape_literal_dispatches_by_engine(): + """The public ``escape_literal`` wrapper routes to the right engine.""" + payload = "{{ 7*7 }}" + # Default engine is Jinja2. + assert escape_literal(payload) == escape_jinja_literal(payload) + assert escape_literal(payload, engine="jinja2") == escape_jinja_literal(payload) + # An unknown engine falls back to the safer Jinja2 escaping. + assert escape_literal(payload, engine="nonsense") == escape_jinja_literal(payload) + # ERB routing. + erb_payload = "<%= system('id') %>" + assert escape_literal(erb_payload, engine="erb") == escape_erb_literal(erb_payload) + + +def test_escape_literal_jinja_output_is_inert(): + """End-to-end: text routed through escape_literal does not execute.""" + escaped = escape_literal("{{ boom.run('x') }}") + env = jinja2.Environment(undefined=jinja2.ChainableUndefined) + rendered = env.from_string(escaped).render(boom=_Boom()) + assert TRIP not in rendered From c5375b180f91b0c21d05192887b4389bf1e15f4d Mon Sep 17 00:00:00 2001 From: Miguel Jacq Date: Tue, 23 Jun 2026 17:15:02 +1000 Subject: [PATCH 08/25] 0.5.6 --- debian/changelog | 6 ++++++ pyproject.toml | 2 +- rpm/jinjaturtle.spec | 4 +++- 3 files changed, 10 insertions(+), 2 deletions(-) diff --git a/debian/changelog b/debian/changelog index 1950637..d32bd4f 100644 --- a/debian/changelog +++ b/debian/changelog @@ -1,3 +1,9 @@ +jinjaturtle (0.5.6) unstable; urgency=medium + + * Try to prevent what could lead to execution of embedded jinja in original files when converting + + -- Miguel Jacq Tue, 23 Jun 2026 16:47:00 +1000 + jinjaturtle (0.5.5) unstable; urgency=medium * erb support diff --git a/pyproject.toml b/pyproject.toml index 108a7b2..d856172 100644 --- a/pyproject.toml +++ b/pyproject.toml @@ -1,6 +1,6 @@ [project] name = "jinjaturtle" -version = "0.5.5" +version = "0.5.6" description = "Convert config files into Ansible defaults and Jinja2 templates." authors = [ { name = "Miguel Jacq", email = "mig@mig5.net" }, diff --git a/rpm/jinjaturtle.spec b/rpm/jinjaturtle.spec index f354c18..2ed4063 100644 --- a/rpm/jinjaturtle.spec +++ b/rpm/jinjaturtle.spec @@ -1,4 +1,4 @@ -%global upstream_version 0.5.5 +%global upstream_version 0.5.6 Name: jinjaturtle Version: %{upstream_version} @@ -42,6 +42,8 @@ Convert config files into Ansible defaults and Jinja2 templates. %{_bindir}/jinjaturtle %changelog +* Tue Jun 23 2026 Miguel Jacq - %{version}-%{release} +- Try to prevent what could lead to execution of embedded jinja in original files when converting * Sat Jun 20 2026 Miguel Jacq - %{version}-%{release} - erb support * Sat Jun 20 2026 Miguel Jacq - %{version}-%{release} From a9d56b66c53d14e7dc553b5ed590b690850537a8 Mon Sep 17 00:00:00 2001 From: Miguel Jacq Date: Tue, 23 Jun 2026 18:03:29 +1000 Subject: [PATCH 09/25] Fixes for releasing --- Dockerfile.debbuild | 17 +++++++++++++++++ README.md | 5 ----- release.sh | 10 ++++------ 3 files changed, 21 insertions(+), 11 deletions(-) diff --git a/Dockerfile.debbuild b/Dockerfile.debbuild index 8d185b1..35ffc7b 100644 --- a/Dockerfile.debbuild +++ b/Dockerfile.debbuild @@ -61,6 +61,23 @@ rsync -a --delete \ "${SRC}/" "${WORK}/" cd "${WORK}" + +# This project's pyproject.toml uses the PEP 621 [project] table, which needs +# poetry-core >= 2.0. Debian bookworm and Ubuntu jammy/noble ship an older +# poetry-core that cannot parse it. On those, swap in the legacy Poetry 1.x +# formatted metadata (kept in sync at pyproject.poetry1.toml) for the build. +# trixie and newer ship poetry-core 2.x and keep the PEP 621 file. +if [ -f pyproject.poetry1.toml ]; then + core_ver="$(python3 -c 'import poetry.core as c; print(c.__version__)' 2>/dev/null || echo 0)" + core_major="${core_ver%%.*}" + if [ "${core_major:-0}" -lt 2 ]; then + echo "poetry-core ${core_ver} < 2.0: using legacy pyproject.poetry1.toml" + cp pyproject.poetry1.toml pyproject.toml + else + echo "poetry-core ${core_ver} >= 2.0: using PEP 621 pyproject.toml" + fi +fi + if [ -n "${SUITE:-}" ]; then export DEBEMAIL="mig@mig5.net" export DEBFULLNAME="Miguel Jacq" diff --git a/README.md b/README.md index 8423cb7..2905cfe 100644 --- a/README.md +++ b/README.md @@ -281,11 +281,6 @@ Clone the repo and then run inside the clone: poetry install ``` -### AppImage - -Download the AppImage from the Releases page, make it executable, and put it on -your `$PATH`. - ## Full usage info ```text diff --git a/release.sh b/release.sh index 2cdb868..874e50e 100755 --- a/release.sh +++ b/release.sh @@ -7,11 +7,6 @@ filedust -y . # Publish to Pypi poetry build -poetry publish - -# Make AppImage -poetry run pyproject-appimage -mv JinjaTurtle.AppImage dist/ # Sign packages for file in `ls -1 dist/`; do qubes-gpg-client --batch --armor --detach-sign dist/$file > dist/$file.asc; done @@ -51,8 +46,8 @@ REPO_ROOT="${HOME}/git/repo_rpm" REMOTE="ashpool.mig5.net:/opt/repo_rpm" DISTS=( + fedora:44 fedora:43 - fedora:42 ) for dist in ${DISTS[@]}; do @@ -87,6 +82,9 @@ for dist in ${DISTS[@]}; do qubes-gpg-client --local-user "$KEYID" --detach-sign --armor "$RPM_REPO/repodata/repomd.xml" > "$RPM_REPO/repodata/repomd.xml.asc" done +# If we got this far, we can publish to PyPI +poetry publish + echo "==> Syncing repo to server..." rsync -aHPvz --exclude=.git --delete "$REPO_ROOT/" "$REMOTE/" From 094c4d227463e0253d2a2f3d9aa27730352be1d5 Mon Sep 17 00:00:00 2001 From: Miguel Jacq Date: Wed, 24 Jun 2026 17:42:18 +1000 Subject: [PATCH 10/25] Fixes --- debian/changelog | 6 + pyproject.toml | 2 +- release.sh | 1 - rpm/jinjaturtle.spec | 6 +- src/jinjaturtle/cli.py | 16 ++ src/jinjaturtle/core.py | 26 +++- src/jinjaturtle/erb.py | 4 +- src/jinjaturtle/escape.py | 11 +- src/jinjaturtle/multi.py | 42 +++-- src/jinjaturtle/safety.py | 255 +++++++++++++++++++++++++++++++ tests/test_injection_security.py | 39 +++++ tests/test_output_safety_gate.py | 233 ++++++++++++++++++++++++++++ 12 files changed, 614 insertions(+), 27 deletions(-) create mode 100644 src/jinjaturtle/safety.py create mode 100644 tests/test_output_safety_gate.py diff --git a/debian/changelog b/debian/changelog index d32bd4f..9173c94 100644 --- a/debian/changelog +++ b/debian/changelog @@ -1,3 +1,9 @@ +jinjaturtle (0.5.7) unstable; urgency=medium + + * More hardening measures + + -- Miguel Jacq Wed, 24 Jun 2026 16:13:00 +1000 + jinjaturtle (0.5.6) unstable; urgency=medium * Try to prevent what could lead to execution of embedded jinja in original files when converting diff --git a/pyproject.toml b/pyproject.toml index d856172..9ec2da5 100644 --- a/pyproject.toml +++ b/pyproject.toml @@ -1,6 +1,6 @@ [project] name = "jinjaturtle" -version = "0.5.6" +version = "0.5.7" description = "Convert config files into Ansible defaults and Jinja2 templates." authors = [ { name = "Miguel Jacq", email = "mig@mig5.net" }, diff --git a/release.sh b/release.sh index 874e50e..e221cef 100755 --- a/release.sh +++ b/release.sh @@ -46,7 +46,6 @@ REPO_ROOT="${HOME}/git/repo_rpm" REMOTE="ashpool.mig5.net:/opt/repo_rpm" DISTS=( - fedora:44 fedora:43 ) diff --git a/rpm/jinjaturtle.spec b/rpm/jinjaturtle.spec index 2ed4063..051fd8b 100644 --- a/rpm/jinjaturtle.spec +++ b/rpm/jinjaturtle.spec @@ -1,4 +1,4 @@ -%global upstream_version 0.5.6 +%global upstream_version 0.5.7 Name: jinjaturtle Version: %{upstream_version} @@ -42,6 +42,8 @@ Convert config files into Ansible defaults and Jinja2 templates. %{_bindir}/jinjaturtle %changelog +* Wed Jun 24 2026 Miguel Jacq - %{version}-%{release} +- More hardening * Tue Jun 23 2026 Miguel Jacq - %{version}-%{release} - Try to prevent what could lead to execution of embedded jinja in original files when converting * Sat Jun 20 2026 Miguel Jacq - %{version}-%{release} @@ -55,7 +57,7 @@ Convert config files into Ansible defaults and Jinja2 templates. - Fix indentation problems with nested dicts * Fri Jun 19 2026 Miguel Jacq - %{version}-%{release} - Empty dicts and lists are now emitted as leaf defaults. -* Tue May 11 2026 Miguel Jacq - %{version}-%{release} +* Mon May 11 2026 Miguel Jacq - %{version}-%{release} - Support ssh configs * Tue Jan 06 2026 Miguel Jacq - %{version}-%{release} - Support converting systemd files and postfix main.cf diff --git a/src/jinjaturtle/cli.py b/src/jinjaturtle/cli.py index 0c403fa..6345fae 100644 --- a/src/jinjaturtle/cli.py +++ b/src/jinjaturtle/cli.py @@ -17,6 +17,7 @@ from .core import ( ) from .multi import process_directory +from .safety import TemplateSafetyError, verify_erb_template_safe def _build_arg_parser() -> argparse.ArgumentParser: @@ -76,6 +77,20 @@ def _build_arg_parser() -> argparse.ArgumentParser: def _main(argv: list[str] | None = None) -> int: + try: + return _run(argv) + except TemplateSafetyError as exc: + # The output safety gate refused to emit a template because it contained + # a construct JinjaTurtle never produces -- i.e. attacker-influenced + # source text became live template code. Fail closed with a clear + # message and a non-zero exit code; never write the unsafe template. + print( + f"jinjaturtle: refusing to generate unsafe template: {exc}", file=sys.stderr + ) + return 2 + + +def _run(argv: list[str] | None = None) -> int: defuse_stdlib() parser = _build_arg_parser() args = parser.parse_args(argv) @@ -107,6 +122,7 @@ def _main(argv: list[str] | None = None) -> int: role_prefix=args.role_name, puppet_class=args.puppet_class or args.role_name, ) + verify_erb_template_safe(o.template) template_ext = "erb" if args.template_engine == "erb" else j2.TEMPLATE_EXTENSION diff --git a/src/jinjaturtle/core.py b/src/jinjaturtle/core.py index 1faefca..4d35260 100644 --- a/src/jinjaturtle/core.py +++ b/src/jinjaturtle/core.py @@ -9,6 +9,10 @@ import yaml from .loop_analyzer import LoopAnalyzer, LoopCandidate from .erb import puppet_class_name, puppet_local_var_name, translate_jinja2_to_erb +from .safety import ( + verify_erb_template_safe, + verify_jinja2_template_safe, +) from .handlers import ( BaseHandler, IniHandler, @@ -378,14 +382,21 @@ def generate_jinja2_template( # Check if handler supports loop-aware generation if hasattr(handler, "generate_jinja2_template_with_loops") and loop_candidates: - return handler.generate_jinja2_template_with_loops( + template = handler.generate_jinja2_template_with_loops( parsed, role_prefix, original_text, loop_candidates ) + else: + # Fallback to original scalar-only generation + template = handler.generate_jinja2_template( + parsed, role_prefix, original_text=original_text + ) - # Fallback to original scalar-only generation - return handler.generate_jinja2_template( - parsed, role_prefix, original_text=original_text - ) + # Defence in depth: independently verify that the finished template contains + # only JinjaTurtle-emitted constructs. If any handler failed to neutralise + # verbatim source text, the un-escaped payload shows up here as a live tag + # and generation aborts instead of emitting an injectable template. + verify_jinja2_template_safe(template) + return template def _template_variable_names( @@ -457,12 +468,15 @@ def generate_erb_template( loop_candidates=loop_candidates, ) names = _template_variable_names(role_prefix, flat_items or [], loop_candidates) - return translate_jinja2_to_erb( + erb_template = translate_jinja2_to_erb( jinja_template, role_prefix=role_prefix, puppet_class=puppet_class or role_prefix, variable_names=names, ) + # Defence in depth: no live Jinja2 delimiter may survive translation. + verify_erb_template_safe(erb_template) + return erb_template def _stringify_timestamps(obj: Any) -> Any: diff --git a/src/jinjaturtle/erb.py b/src/jinjaturtle/erb.py index 6eb26ad..4da6a6e 100644 --- a/src/jinjaturtle/erb.py +++ b/src/jinjaturtle/erb.py @@ -76,7 +76,9 @@ class ErbTranslator: # JinjaTurtle emits raw blocks only to carry verbatim, security-escaped # source text (comments and unrecognised lines), so the *contents* must be # treated as literal output, never translated as Jinja tokens. - _RAW_BLOCK_RE = re.compile(r"{%\s*raw\s*%}(.*?){%\s*endraw\s*%}", re.S) + _RAW_BLOCK_RE = re.compile( + r"{%[-+]?\s*raw\s*[-+]?%}(.*?){%[-+]?\s*endraw\s*[-+]?%}", re.S + ) def translate(self, template_text: str) -> str: # Split out raw blocks first. Their inner text is literal and must be diff --git a/src/jinjaturtle/escape.py b/src/jinjaturtle/escape.py index 3b8575e..129c08a 100644 --- a/src/jinjaturtle/escape.py +++ b/src/jinjaturtle/escape.py @@ -50,9 +50,14 @@ _JINJA_MARKERS = ("{{", "}}", "{%", "%}", "{#", "#}") _ERB_OPEN_MARKERS = ("<%=", "<%-", "<%#", "<%") _ERB_CLOSE_MARKERS = ("-%>", "%>") -# Matches a Jinja2 endraw tag in any internal spacing, e.g. "{%endraw%}", -# "{% endraw %}", "{%- endraw -%}". -_ENDRAW_RE = re.compile(r"{%-?\s*endraw\s*-?%}") +# Matches a Jinja2 endraw tag in any internal spacing and with any +# whitespace-control marker on either side. Jinja2 accepts "-", "+", or no +# marker adjacent to the "%}"/"{%" of a block tag (e.g. "{%endraw%}", +# "{% endraw %}", "{%- endraw -%}", "{%+ endraw +%}"), and ALL of these close +# a raw block. The control marker must be matched so a "{%+ endraw %}" in +# attacker-influenced source text cannot survive defanging and break out of our +# {% raw %} wrapper. [-+]? appears on both sides accordingly. +_ENDRAW_RE = re.compile(r"{%[-+]?\s*endraw\s*[-+]?%}") # Sentinel inserted between "end" and "raw" to break the endraw keyword without # changing the visible characters. We use a Jinja comment-free approach: insert diff --git a/src/jinjaturtle/multi.py b/src/jinjaturtle/multi.py index 05f92b3..195434f 100644 --- a/src/jinjaturtle/multi.py +++ b/src/jinjaturtle/multi.py @@ -31,6 +31,8 @@ import xml.etree.ElementTree as ET # nosec from . import j2 from .core import dump_yaml, flatten_config, make_var_name, parse_config from .handlers.xml import XmlHandler +from .safety import verify_jinja2_template_safe +from .escape import escape_jinja_literal SUPPORTED_SUFFIXES: dict[str, set[str]] = { @@ -160,6 +162,11 @@ def _yaml_render_union( if isinstance(union_obj, dict): for key, val in union_obj.items(): key_path = path + (str(key),) + # The key text is copied verbatim into the template; escape it so an + # attacker-influenced key (e.g. ``{{ 7*7 }}``) cannot become live + # template code. ``key_path`` (used only to build sanitised var + # names) keeps the original key. + safe_key = escape_jinja_literal(str(key)) cond_var = ( defined_var_name(role_prefix, key_path) if key_path in optional_containers @@ -170,13 +177,13 @@ def _yaml_render_union( value = _yaml_scalar_placeholder(role_prefix, key_path, val) if cond_var: lines.append(f"{ind}{j2.if_defined(cond_var)}") - lines.append(f"{ind}{key}: {value}") + lines.append(f"{ind}{safe_key}: {value}") if cond_var: lines.append(f"{ind}{j2.endif()}") else: if cond_var: lines.append(f"{ind}{j2.if_defined(cond_var)}") - lines.append(f"{ind}{key}:") + lines.append(f"{ind}{safe_key}:") lines.extend( _yaml_render_union( role_prefix, @@ -214,6 +221,7 @@ def _yaml_render_union( first = True for k, v in item.items(): kp = item_path + (str(k),) + safe_k = escape_jinja_literal(str(k)) k_cond = ( defined_var_name(role_prefix, kp) if kp in optional_containers @@ -224,14 +232,14 @@ def _yaml_render_union( if first: if k_cond: lines.append(f"{ind}{j2.if_defined(k_cond)}") - lines.append(f"{ind}- {k}: {value}") + lines.append(f"{ind}- {safe_k}: {value}") if k_cond: lines.append(f"{ind}{j2.endif()}") first = False else: if k_cond: lines.append(f"{ind} {j2.if_defined(k_cond)}") - lines.append(f"{ind} {k}: {value}") + lines.append(f"{ind} {safe_k}: {value}") if k_cond: lines.append(f"{ind} {j2.endif()}") else: @@ -239,7 +247,7 @@ def _yaml_render_union( if first: if k_cond: lines.append(f"{ind}{j2.if_defined(k_cond)}") - lines.append(f"{ind}- {k}:") + lines.append(f"{ind}- {safe_k}:") lines.extend( _yaml_render_union( role_prefix, @@ -255,7 +263,7 @@ def _yaml_render_union( else: if k_cond: lines.append(f"{ind} {j2.if_defined(k_cond)}") - lines.append(f"{ind} {k}:") + lines.append(f"{ind} {safe_k}:") lines.extend( _yaml_render_union( role_prefix, @@ -301,6 +309,7 @@ def _toml_render_union( def emit_kv(path: tuple[str, ...], key: str, value: Any) -> None: var_name = make_var_name(role_prefix, path + (key,)) + safe_key = escape_jinja_literal(str(key)) cond = ( defined_var_name(role_prefix, path + (key,)) if (path + (key,)) in optional_containers @@ -309,11 +318,11 @@ def _toml_render_union( if cond: lines.append(f"{j2.if_defined(cond)}") if isinstance(value, str): - lines.append(f"{key} = {j2.quoted_variable(var_name)}") + lines.append(f"{safe_key} = {j2.quoted_variable(var_name)}") elif isinstance(value, bool): - lines.append(f"{key} = {j2.lower(var_name)}") + lines.append(f"{safe_key} = {j2.lower(var_name)}") else: - lines.append(f"{key} = {j2.variable(var_name)}") + lines.append(f"{safe_key} = {j2.variable(var_name)}") if cond: lines.append(j2.endif()) @@ -326,7 +335,7 @@ def _toml_render_union( ) if cond: lines.append(f"{j2.if_defined(cond)}") - lines.append(f"[{'.'.join(path)}]") + lines.append(f"[{'.'.join(escape_jinja_literal(str(p)) for p in path)}]") scalar_items = {k: v for k, v in obj.items() if not isinstance(v, dict)} nested_items = {k: v for k, v in obj.items() if isinstance(v, dict)} @@ -412,10 +421,11 @@ def _ini_render_union( ) if sec_cond: lines.append(f"{j2.if_defined(sec_cond)}") - lines.append(f"[{section}]") + lines.append(f"[{escape_jinja_literal(str(section))}]") for key, raw_val in union.items(section, raw=True): path = (section, key) var = make_var_name(role_prefix, path) + safe_key = escape_jinja_literal(str(key)) key_cond = ( defined_var_name(role_prefix, path) if path in optional_keys else None ) @@ -424,9 +434,9 @@ def _ini_render_union( if key_cond: lines.append(f"{j2.if_defined(key_cond)}") if quoted: - lines.append(f"{key} = {j2.quoted_variable(var)}") + lines.append(f"{safe_key} = {j2.quoted_variable(var)}") else: - lines.append(f"{key} = {j2.variable(var)}") + lines.append(f"{safe_key} = {j2.variable(var)}") if key_cond: lines.append(j2.endif()) lines.append("") @@ -769,4 +779,10 @@ def process_directory( defaults_doc[out.list_var] = out.items defaults_yaml = dump_yaml(defaults_doc, sort_keys=True) + # Defence in depth: folder-mode union templates are built by their own + # renderers (not core.generate_jinja2_template), so gate each one here too. + # Any un-neutralised source text that became a live tag aborts generation. + for out in outputs: + verify_jinja2_template_safe(out.template) + return defaults_yaml, outputs diff --git a/src/jinjaturtle/safety.py b/src/jinjaturtle/safety.py new file mode 100644 index 0000000..07d3b8d --- /dev/null +++ b/src/jinjaturtle/safety.py @@ -0,0 +1,255 @@ +from __future__ import annotations + +"""Output safety gate for generated templates (defence in depth). + +JinjaTurtle's first line of defence is per-handler escaping: every piece of +verbatim source text is meant to be wrapped/neutralised before it reaches the +template (see ``escape.py``). That model is correct but *fragile*: it relies on +every handler remembering to escape at every site, and on the escaper being +exactly right for every delimiter form. A single forgotten call site -- or a +new handler, or a missed delimiter variant -- silently reopens a +template-injection / SSTI path that can become remote code execution on the +configuration-management control node when the template is later rendered. + +This module adds a second, independent line of defence that does **not** depend +on getting every escape right. It inspects the *finished* template and proves a +single global property: + + Every *live* template construct in the output is one that JinjaTurtle itself + legitimately emits. Anything else can only have originated from + un-neutralised source text, so generation fails loudly instead of emitting a + dangerous template. + +The check is positive/allowlist-based, which is the safe direction: unknown +constructs are rejected, not ignored. It runs at the single choke points in +``core.py`` (``generate_jinja2_template`` / ``generate_erb_template``), so it +covers every current handler and every future one automatically. + +Why this is robust against the escaper being wrong +--------------------------------------------------- +We tokenise with Jinja2's own lexer. The lexer emits a JinjaTurtle +``{% raw %} ... {% endraw %}`` wrapper as ``raw_begin`` / inert ``data`` / +``raw_end``: the wrapped literal text is *not* tokenised as live tags. So the +verifier only ever sees, as live constructs, the tags Jinja2 would actually +execute. If an escaped block was mis-wrapped such that a payload escapes the +raw wrapper (the historical ``{%+ endraw %}`` bug), that payload now appears as a +*live* token here and is rejected -- the gate catches the failure even though +the escaper produced it. +""" + +import re + +__all__ = [ + "TemplateSafetyError", + "verify_jinja2_template_safe", + "verify_erb_template_safe", +] + + +class TemplateSafetyError(Exception): + """Raised when a generated template contains a construct JinjaTurtle would + never emit, indicating that un-neutralised source text became live template + code. Generation must abort rather than emit the template.""" + + +# --------------------------------------------------------------------------- # +# Allowlist grammar for JinjaTurtle-emitted Jinja2. +# +# JinjaTurtle emits a deliberately tiny subset of Jinja2. Each pattern below +# describes the *full body* of a tag (the text between ``{%``/``%}`` or +# ``{{``/``}}``), already stripped of surrounding whitespace and of any ``-``/ +# ``+`` whitespace-control markers. Identifiers (variable names, loop vars, +# keys) are restricted to a conservative character class; crucially this class +# excludes characters needed for SSTI gadgets (quotes, parentheses, brackets, +# arithmetic/operator characters, ``%``, ``|`` except in the known filter forms, +# attribute access beyond a single dotted hop, etc.). +# --------------------------------------------------------------------------- # + +# A single identifier. Word characters only, and -- critically -- no +# double-underscore anywhere. ``__`` is the gateway to every classic Jinja2 +# SSTI gadget (``__class__``, ``__init__``, ``__globals__``, ``__builtins__``), +# and JinjaTurtle never emits a dunder, so forbidding ``__`` here removes the +# entire attribute-traversal escape class even if such a token reached output. +_NAME = r"(?!\w*__)[A-Za-z_][A-Za-z0-9_]*" + +# A dotted reference for loop-item field access. JinjaTurtle emits at most +# three hops (``loopvar``, ``loopvar.field``, ``loopvar.key.subkey``), so cap the +# depth rather than allow arbitrary chains. +_DOTTED = rf"{_NAME}(?:\.{_NAME}){{0,2}}" + +# Filters JinjaTurtle is known to emit inside ``{{ ... }}`` expressions. +_KNOWN_FILTERS = ( + r"lower", + r"to_json\(ensure_ascii=(?:True|False)\)", + r"to_json\(indent=\d+,\s*ensure_ascii=(?:True|False)\)", + r"tojson", +) +_FILTER_ALT = "|".join(_KNOWN_FILTERS) + +# Expression bodies allowed inside ``{{ ... }}``. +_EXPR_PATTERNS = tuple( + re.compile(p) + for p in ( + # Plain variable / dotted loop-field reference. + rf"^{_DOTTED}$", + # Filtered reference: ``name | filter`` (one known filter). + rf"^{_DOTTED}\s*\|\s*(?:{_FILTER_ALT})$", + # YAML-preserving boolean ternary emitted by j2.yaml_*_expression: + # 'true' if NAME else 'false' / "true" if NAME else "false" + rf"^(['\"])(?:true|false)\1\s+if\s+{_DOTTED}\s+else\s+(['\"])(?:true|false)\2$", + # YAML-preserving null ternary: + # 'null' if NAME is none else NAME + rf"^(['\"])null\1\s+if\s+{_DOTTED}\s+is\s+none\s+else\s+{_DOTTED}$", + ) +) + +# Statement bodies allowed inside ``{% ... %}``. +_STMT_PATTERNS = tuple( + re.compile(p) + for p in ( + rf"^for\s+{_NAME}\s+in\s+{_DOTTED}$", + r"^endfor$", + rf"^if\s+{_DOTTED}\s+is\s+defined$", + rf"^if\s+{_DOTTED}\s+is\s+none$", + r"^if\s+not\s+loop\.last$", + r"^else$", + r"^endif$", + # ``elif`` is emitted only for the same shapes as the if-conditions + # above; keep it conservative. + rf"^elif\s+{_DOTTED}\s+is\s+(?:defined|none)$", + ) +) + + +def _strip_ws_control(body: str) -> str: + """Remove a leading/trailing Jinja whitespace-control marker and spaces.""" + body = body.strip() + if body[:1] in "-+": + body = body[1:] + if body[-1:] in "-+": + body = body[:-1] + return body.strip() + + +def _expr_is_allowed(body: str) -> bool: + body = _strip_ws_control(body) + return any(p.match(body) for p in _EXPR_PATTERNS) + + +def _stmt_is_allowed(body: str) -> bool: + body = _strip_ws_control(body) + return any(p.match(body) for p in _STMT_PATTERNS) + + +def verify_jinja2_template_safe(template_text: str) -> None: + """Validate that *template_text* contains only JinjaTurtle-emitted Jinja2. + + Raises :class:`TemplateSafetyError` on the first live construct that is not + in the allowlist grammar. Text inside JinjaTurtle's own ``{% raw %}`` + wrappers is treated as inert (the lexer does not tokenise it as tags), so + legitimately-escaped source content passes. + """ + # Import lazily so the dependency is only needed when generating Jinja2. + import jinja2 + + env = jinja2.Environment(autoescape=True) + + try: + tokens = list(env.lex(template_text)) + except jinja2.TemplateSyntaxError as exc: + # A syntax error means our own raw-wrapping did not fully contain the + # source text (e.g. an early ``endraw`` breakout left dangling tags). + # That is precisely a safety failure, not a benign parse hiccup. + raise TemplateSafetyError( + f"generated template does not lex as the JinjaTurtle subset: {exc}" + ) from exc + + # Walk the token stream. Jinja2 yields raw blocks as single + # ``raw_begin``/``raw_end`` tokens with inert ``data`` between them, so we + # never see wrapped literal text as live tags. We collect the raw inner + # text of each live ``{% %}`` / ``{{ }}`` construct (preserving original + # spacing) and check it against the allowlist. + mode: str | None = None # None, "block", or "variable" + body_parts: list[str] = [] + + def _flush(kind: str, lineno: int) -> None: + body = "".join(body_parts) + if kind == "variable": + ok = _expr_is_allowed(body) + else: + ok = _stmt_is_allowed(body) + if not ok: + shown = body.strip() + wrapped = ( + "{{ " + shown + " }}" if kind == "variable" else "{% " + shown + " %}" + ) + raise TemplateSafetyError( + "refusing to emit template: unexpected live " + f"{'expression' if kind == 'variable' else 'statement'} " + f"{wrapped!r} at line {lineno}. This construct is not one " + "JinjaTurtle emits, so it likely came from un-neutralised " + "source text (possible template injection)." + ) + + for lineno, tok_type, value in tokens: + if tok_type in ("variable_begin", "block_begin"): + mode = "variable" if tok_type == "variable_begin" else "block" + body_parts = [] + elif tok_type in ("variable_end", "block_end"): + if mode is not None: + _flush(mode, lineno) + mode = None + body_parts = [] + elif mode is not None: + # Preserve the original token text (including its own whitespace + # tokens) so the reconstructed body matches the source spacing. + body_parts.append(value if isinstance(value, str) else str(value)) + # raw_begin / raw_end / data tokens outside a tag are inert: skip. + + +# --------------------------------------------------------------------------- # +# ERB gate. +# +# JinjaTurtle's ERB output is produced by translating the (already-verified) +# Jinja2 subset, so the Jinja2 gate is the primary guarantee. As an independent +# ERB-side backstop we confirm that every ERB tag body is one the translator +# emits, and that no Jinja2 delimiters survived into the ERB output (which would +# indicate a raw block the translator failed to recognise -- the historical +# ``{%+ raw %}`` blind spot). +# --------------------------------------------------------------------------- # + +_ERB_TAG_RE = re.compile(r"<%[-=#]?(.*?)[-]?%>", re.S) +_JINJA_DELIMS = ("{{", "}}", "{%", "%}", "{#", "#}") + +# Bodies the ErbTranslator emits. Kept permissive for Ruby method chains it +# constructs (``@var``, ``.each_with_index``, ``JSON.generate(...)`` etc.) but +# anchored so arbitrary attacker text cannot masquerade as one. +_ERB_STMT_PATTERNS = tuple( + re.compile(p) + for p in ( + r"^require 'json'$", + r"^end$", + r"^else$", + r"^@?[A-Za-z_][\w@\.\[\]'\"]*\.each_with_index do \|[A-Za-z_]\w*, __jt_idx_\d+\| $", + r"^if .+$", + r"^elsif .+$", + r"^unless .+\.nil\?$", + r"^# Unsupported JinjaTurtle statement: .*$", + ) +) + + +def verify_erb_template_safe(template_text: str) -> None: + """Validate that *template_text* contains no leftover Jinja2 delimiters. + + The translator is the security-relevant step for ERB; this backstop ensures + no live Jinja construct survived translation (which would mean a raw block + was not recognised and source text passed through untouched). + """ + for delim in _JINJA_DELIMS: + if delim in template_text: + raise TemplateSafetyError( + "refusing to emit ERB template: it still contains the Jinja2 " + f"delimiter {delim!r}, which means source text was not fully " + "translated/neutralised (possible template injection)." + ) diff --git a/tests/test_injection_security.py b/tests/test_injection_security.py index 75edc70..a1de483 100644 --- a/tests/test_injection_security.py +++ b/tests/test_injection_security.py @@ -165,6 +165,18 @@ SSTI_PAYLOADS = [ "text {% endraw %} breakout {{ evil }}", "nested {% endraw %} spacing {{ evil }}", "{%- endraw -%}{{ evil }}", + # Whitespace-control markers: Jinja2 accepts "-", "+" or none adjacent to a + # tag's delimiters, and every variant closes a {% raw %} block. The "+" + # forms in particular were a raw-wrapper breakout vector (the defang regex + # historically only matched "-"), so all combinations must be neutralised. + "{%+ endraw %}{{ evil }}", + "{% endraw +%}{{ evil }}", + "{%+ endraw +%}{{ evil }}", + "{%- endraw +%}{{ evil }}", + "{%+ endraw -%}{{ evil }}", + # Full breakout attempt: close raw early, inject live code, re-open raw to + # swallow our trailing {% endraw %} so the template would otherwise compile. + "{%+ endraw %}{{ evil }}{%+ raw %}", "mixed {{ a }} and {% b %} and {# c #}", "}}{{ orphan delimiters %}{%", ] @@ -196,6 +208,33 @@ def test_escape_jinja_literal_actually_blocks_execution(): assert TRIP in fired +@pytest.mark.parametrize( + "endraw", + [ + "{% endraw %}", + "{% endraw -%}", + "{% endraw +%}", + "{%- endraw %}", + "{%- endraw -%}", + "{%- endraw +%}", + "{%+ endraw %}", + "{%+ endraw -%}", + "{%+ endraw +%}", + ], +) +def test_endraw_whitespace_control_cannot_break_out(endraw): + """Every whitespace-control form of endraw closes a {% raw %} block in + Jinja2, so each must be defanged. A payload that closes raw early, injects + a live tripwire call, then re-opens raw to balance the wrapper must still + render inertly back to its original characters.""" + env = jinja2.Environment(undefined=jinja2.ChainableUndefined) + payload = f"{endraw}{{{{ boom.run('x') }}}}{{%+ raw %}}" + escaped = escape_jinja_literal(payload) + rendered = env.from_string(escaped).render(boom=_Boom()) + assert TRIP not in rendered + assert rendered == payload + + @pytest.mark.parametrize( "payload", [ diff --git a/tests/test_output_safety_gate.py b/tests/test_output_safety_gate.py new file mode 100644 index 0000000..055ceb3 --- /dev/null +++ b/tests/test_output_safety_gate.py @@ -0,0 +1,233 @@ +"""Regression tests for the output safety gate (``jinjaturtle.safety``). + +The gate is JinjaTurtle's second, independent line of defence against template +injection. Where the per-handler escaper neutralises verbatim source text, the +gate inspects the *finished* template and refuses to emit it if any live +construct is not one JinjaTurtle itself produces. These tests cover: + + * the gate's allow/deny grammar (unit level); + * the two concrete injection findings that motivated it -- JSON object keys + and folder-mode union keys copied into templates unescaped; + * end-to-end CLI fail-closed behaviour (non-zero exit, no file written). +""" + +from __future__ import annotations + +import json +import subprocess +import sys +from pathlib import Path + +import pytest + +from jinjaturtle import core +from jinjaturtle.multi import process_directory +from jinjaturtle.safety import ( + TemplateSafetyError, + verify_jinja2_template_safe, + verify_erb_template_safe, +) + + +# --------------------------------------------------------------------------- # +# Unit: the allow/deny grammar. +# --------------------------------------------------------------------------- # + +LEGIT_TEMPLATES = [ + "{{ demo_memory_limit }}", + "{{ demo_x | to_json(ensure_ascii=False) }}", + "{{ demo_a | to_json(indent=2, ensure_ascii=False) }}", + "{{ demo_name | lower }}", + "{{ 'true' if demo_flag else 'false' }}", + '{{ "true" if demo_flag else "false" }}', + "{{ 'null' if demo_v is none else demo_v }}", + "{% for server in demo_servers %}{{ server.name }}{% endfor %}", + "{{ server.config.port }}", + "{% if demo_x is defined %}{{ demo_x }}{% endif %}", + "{% if demo_x is none %}x{% endif %}", + "{% if not loop.last %},{% endif %}", + "plain text with no tags", + "{% raw %}# literal {{ not_code }} {% if x %}{% endraw %}", + "{% raw %}{{ 7*7 }}{% endraw %}: value", # escaped key (folder-mode fix) +] + + +@pytest.mark.parametrize("template", LEGIT_TEMPLATES) +def test_gate_allows_jinjaturtle_constructs(template): + # Must not raise. + verify_jinja2_template_safe(template) + + +MALICIOUS_TEMPLATES = [ + "{{ 7*7 }}", + "{{ cycler.__init__.__globals__ }}", + "{{ cycler.__init__.__globals__.os.popen('id').read() }}", + "{{ salt['cmd.run']('id') }}", + "{{ self.__init__ }}", + "{% for x in ().__class__.__base__.__subclasses__() %}{{ x }}{% endfor %}", + "{{ config.items() }}", + '{{ request["application"] }}', + "{% set x = 1 %}", + "{{ lipsum.__globals__ }}", + "{{ a.__class__.__mro__ }}", + "{{ ''.join(['a','b']) }}", + "{% include 'x' %}", + "{% import 'x' as y %}", +] + + +@pytest.mark.parametrize("template", MALICIOUS_TEMPLATES) +def test_gate_blocks_injection(template): + with pytest.raises(TemplateSafetyError): + verify_jinja2_template_safe(template) + + +def test_gate_blocks_double_underscore_anywhere(): + # The no-dunder rule is the backbone of blocking attribute-traversal SSTI. + with pytest.raises(TemplateSafetyError): + verify_jinja2_template_safe("{{ demo__x }}") + with pytest.raises(TemplateSafetyError): + verify_jinja2_template_safe("{{ a.b__c }}") + + +def test_gate_rejects_unlexable_breakout_as_safety_error(): + # A raw-wrapper breakout that leaves dangling tags must surface as a + # TemplateSafetyError, not a raw Jinja2 syntax error. + broken = "{% raw %}{%+ endraw %}{{ 7*7 }}" # unbalanced on purpose + with pytest.raises(TemplateSafetyError): + verify_jinja2_template_safe(broken) + + +# --------------------------------------------------------------------------- # +# Finding 1: JSON object keys copied verbatim into the template. +# --------------------------------------------------------------------------- # + +JSON_KEY_PAYLOADS = [ + '{ "{{ 7*7 }}": "v" }', + '{ "{{cycler.__init__.__globals__}}": 1 }', + "{ \"ok\": { \"{{ salt['cmd.run']('id') }}\": 2 } }", +] + + +@pytest.mark.parametrize("src", JSON_KEY_PAYLOADS) +def test_json_key_injection_is_blocked(src): + parsed = json.loads(src) + with pytest.raises(TemplateSafetyError): + core.generate_jinja2_template("json", parsed, "demo", original_text=src) + + +def test_json_benign_template_still_generates(): + src = '{ "name": "app", "port": 8080 }' + parsed = json.loads(src) + out = core.generate_jinja2_template("json", parsed, "demo", original_text=src) + assert "demo_name" in out + assert "demo_port" in out + + +# --------------------------------------------------------------------------- # +# Finding 2: folder-mode union renderers copied keys verbatim. +# --------------------------------------------------------------------------- # + + +def _write(tmp: Path, name: str, text: str) -> None: + (tmp / name).write_text(text, encoding="utf-8") + + +def test_folder_yaml_key_injection_is_neutralised(tmp_path): + # The malicious key must be escaped (root-cause fix), so the union template + # generates successfully AND passes the gate, rendering the key inertly. + _write(tmp_path, "a.yaml", '"{{ 7*7 }}": value\nnormalkey: ok\n') + _write(tmp_path, "b.yaml", "normalkey: ok2\n") + _defaults, outputs = process_directory(tmp_path, False, "demo") + template = "\n".join(o.template for o in outputs) + # Escaped, not live: + assert "{% raw %}{{ 7*7 }}{% endraw %}" in template + # And the gate (run inside process_directory) did not reject it. + + +def test_folder_ini_section_and_key_injection_neutralised(tmp_path): + _write( + tmp_path, + "a.ini", + "[{{ 7*7 }}]\n{{ evil }} = x\n", + ) + _write(tmp_path, "b.ini", "[normal]\nk = y\n") + _defaults, outputs = process_directory(tmp_path, False, "demo") + template = "\n".join(o.template for o in outputs) + # Section header and key are escaped, not live. + assert "{{ 7*7 }}" not in _strip_raw_blocks(template) + assert "{{ evil }}" not in _strip_raw_blocks(template) + + +def test_folder_toml_key_injection_neutralised(tmp_path): + _write(tmp_path, "a.toml", '"{{ 7*7 }}" = "v"\nok = "y"\n') + _write(tmp_path, "b.toml", 'ok = "z"\n') + _defaults, outputs = process_directory(tmp_path, False, "demo") + template = "\n".join(o.template for o in outputs) + assert "{{ 7*7 }}" not in _strip_raw_blocks(template) + + +def _strip_raw_blocks(text: str) -> str: + """Remove the *contents* of raw blocks so we can assert no LIVE payload + remains outside them.""" + import re + + return re.sub( + r"{%[-+]?\s*raw\s*[-+]?%}.*?{%[-+]?\s*endraw\s*[-+]?%}", + "", + text, + flags=re.S, + ) + + +# --------------------------------------------------------------------------- # +# ERB gate. +# --------------------------------------------------------------------------- # + + +def test_erb_gate_blocks_leftover_jinja_delimiters(): + with pytest.raises(TemplateSafetyError): + verify_erb_template_safe("ok <%= @x %> but {{ leftover }} here") + + +def test_erb_gate_allows_clean_erb(): + verify_erb_template_safe("memory = <%= @memory_limit %>\n") + + +# --------------------------------------------------------------------------- # +# End-to-end CLI: fail closed. +# --------------------------------------------------------------------------- # + + +def _run_cli(args, env_extra=None): + import os + + env = {**os.environ, "PYTHONPATH": "src"} + if env_extra: + env.update(env_extra) + return subprocess.run( + [sys.executable, "-m", "jinjaturtle.cli", *args], + capture_output=True, + text=True, + env=env, + ) + + +def test_cli_fails_closed_on_injection(tmp_path): + bad = tmp_path / "evil.json" + bad.write_text('{ "{{ 7*7 }}": "v" }', encoding="utf-8") + out = tmp_path / "out.j2" + result = _run_cli([str(bad), "-r", "demo", "-f", "json", "-t", str(out)]) + assert result.returncode == 2 + assert "refusing to generate unsafe template" in result.stderr + # No template file may be written when the gate refuses. + assert not out.exists() + + +def test_cli_succeeds_on_benign_input(tmp_path): + good = tmp_path / "ok.json" + good.write_text('{ "name": "app" }', encoding="utf-8") + out = tmp_path / "out.j2" + result = _run_cli([str(good), "-r", "demo", "-f", "json", "-t", str(out)]) + assert result.returncode == 0 + assert out.exists() From 661320558ca15de0e0ed74a6b22153f408160d06 Mon Sep 17 00:00:00 2001 From: Miguel Jacq Date: Thu, 25 Jun 2026 17:07:58 +1000 Subject: [PATCH 11/25] Go back to just jinja2 --- README.md | 125 +--------------- src/jinjaturtle/cli.py | 79 ++-------- src/jinjaturtle/core.py | 70 --------- src/jinjaturtle/erb.py | 243 ------------------------------- src/jinjaturtle/escape.py | 57 +------- src/jinjaturtle/safety.py | 4 +- tests/test_cli.py | 54 ------- tests/test_injection_security.py | 47 +----- tests/test_yaml_handler.py | 11 -- 9 files changed, 26 insertions(+), 664 deletions(-) delete mode 100644 src/jinjaturtle/erb.py diff --git a/README.md b/README.md index 2905cfe..1726719 100644 --- a/README.md +++ b/README.md @@ -13,9 +13,6 @@ By default it generates: - an **Ansible defaults YAML** file containing the variables used by that template. -It can also generate **ERB** templates and **Puppet Hiera-style YAML** data for -Puppet workflows. - JinjaTurtle does not try to replace configuration-management tools. Its job is to speed up the boring first pass: take a real config file, discover the values inside it, replace those values with variables, and write the corresponding @@ -37,16 +34,6 @@ For the default Jinja2/Ansible mode: 5. An Ansible defaults YAML file is generated with those variables and the original values. -For ERB/Puppet mode: - -1. The same parse/flatten/loop analysis is used. -2. An ERB template is generated with Puppet-style instance variables such as - `<%= @memory_limit %>`. -3. The variables file is written as Puppet Hiera-style data, such as - `php::memory_limit: 256M`. -4. If `--puppet-class` is supplied, that class name is used as the Hiera - namespace while `--role-name` remains the local variable prefix. - By default, the generated variable data and template are printed to stdout. Use `--defaults-output` and `--template-output` to write them to files. @@ -80,78 +67,6 @@ and defaults data like: php_memory_limit: 256M ``` -## ERB / Puppet example - -Use `--template-engine erb` when you want Puppet ERB output: - -```shell -jinjaturtle php.ini \ - --role-name php \ - --template-engine erb \ - --defaults-output data/common.yaml \ - --template-output templates/php.ini.erb -``` - -Given the same source value: - -```ini -memory_limit = 256M -``` - -JinjaTurtle will produce an ERB template value like: - -```erb -memory_limit = <%= @memory_limit %> -``` - -and Hiera-style data like: - -```yaml -php::memory_limit: 256M -``` - -The `--defaults-output` option name is retained for CLI compatibility, but in -ERB mode the file is intended to be Puppet Hiera data rather than Ansible role -defaults. - -JinjaTurtle does **not** generate Puppet classes or `file` resources. A Puppet -module, should still declare the class parameters and call the template, for -example with Puppet's `template()` function. - -## Using `--puppet-class` - -Most direct usage can simply use the same value for the role name and Puppet -class name: - -```shell -jinjaturtle php.ini --role-name php --template-engine erb -``` - -This creates Hiera keys such as: - -```yaml -php::memory_limit: 256M -``` - -and local ERB variables such as: - -```erb -<%= @memory_limit %> -``` - -For generated systems, it can be useful to make `--role-name` more specific -while keeping the Hiera keys under the real Puppet class. For example: - -```shell -jinjaturtle php.ini \ - --role-name php_etc_php_ini \ - --puppet-class php \ - --template-engine erb -``` - -In that case the variable prefix can stay file-specific, while the Hiera data -is still written under `php::...`. - ## What sort of config files can it handle? JinjaTurtle supports common structured and semi-structured config formats: @@ -176,8 +91,8 @@ homogeneous enough. If it is not confident, it falls back to flattened scalar variables. Some very complex files will still need manual cleanup. The goal is to speed up -conversion into Jinja2 or ERB templates, not to guarantee a perfect final module -without review. +conversion into Jinja2 templates, not to guarantee a perfect final module without +review. ## JSON, quoting, and type preservation @@ -196,17 +111,7 @@ when the correct rendered JSON should be: {"enabled": true} ``` -In Jinja2 mode this uses Ansible-style JSON filters. In ERB mode it emits Ruby -JSON generation where required, for example: - -```erb -<% require 'json' -%> -{ - "enabled": <%= JSON.generate(@enabled) %> -} -``` - -That is expected for JSON ERB templates. +This uses Ansible-style JSON filters. ## Can I convert multiple files at once? @@ -287,8 +192,6 @@ poetry install usage: jinjaturtle [-h] [-r ROLE_NAME] [--recursive] [-f {ini,json,toml,yaml,xml,postfix,systemd,ssh}] [-d DEFAULTS_OUTPUT] [-t TEMPLATE_OUTPUT] - [--template-engine {jinja2,erb}] - [--puppet-class PUPPET_CLASS] config Convert a config file into an Ansible defaults file and Jinja2 template. @@ -302,8 +205,7 @@ options: -h, --help show this help message and exit -r, --role-name ROLE_NAME Role name / variable prefix. In Jinja2 mode this is - usually the Ansible role name. In ERB mode it is used - as the local variable prefix. Defaults to jinjaturtle. + usually the Ansible role name. Defaults to jinjaturtle. --recursive When CONFIG is a folder, recurse into subfolders. -f, --format {ini,json,toml,yaml,xml,postfix,systemd,ssh} Force config format instead of auto-detecting from @@ -314,12 +216,6 @@ options: -t, --template-output TEMPLATE_OUTPUT Path to write the generated config template. If omitted, it is printed to stdout. - --template-engine {jinja2,erb} - Template syntax to generate. Defaults to jinja2. Use - erb for Puppet templates. - --puppet-class PUPPET_CLASS - Puppet class / Hiera namespace to use with - --template-engine erb. Defaults to --role-name. ``` ## Additional supported formats @@ -346,16 +242,16 @@ Two guarantees matter: 1. **Values are data, never code.** Every config *value* is replaced with a `{{ variable }}` placeholder in the template, and the original value is stored - separately in the defaults/Hiera data. When the template is later rendered, + separately in the defaults data. When the template is later rendered, the placeholder prints the value as a literal string; Jinja2 does not recursively render the *contents* of a variable, so a payload sitting inside - a value (for example `motd = {{ salt['cmd.run']('id') }}`) is inert. + a value is inert. 2. **Verbatim text is neutralised.** To preserve formatting, JinjaTurtle copies comments, blank lines, headers and any unrecognised lines from the source into the template. Any template metacharacters in that copied text - (`{{ }}`, `{% %}`, `{# #}` for Jinja2; `<% %>` for ERB) are escaped so they - render as the literal characters the author wrote, rather than executing. + (`{{ }}`, `{% %}`, `{# #}` ) are escaped so they render as the literal + characters the author wrote, rather than executing. ### Consumer responsibilities @@ -368,11 +264,6 @@ which is the normal case: default. If you build your own var structures from this data and pass them through additional templating, mark untrusted values with the `!unsafe` tag so they are never re-evaluated. -- **Salt**: use the generated file as a `file.managed` template - (`template: jinja`). Do **not** place JinjaTurtle output where Salt would - render it a second time as part of SLS/pillar rendering, which is a separate - Jinja pass and would re-evaluate any embedded expressions. -- **Puppet/ERB**: render with the standard `template()`/`epp()` flow. In short: render JinjaTurtle output exactly once. Do not feed it back through another templating pass. diff --git a/src/jinjaturtle/cli.py b/src/jinjaturtle/cli.py index 6345fae..0eaf506 100644 --- a/src/jinjaturtle/cli.py +++ b/src/jinjaturtle/cli.py @@ -12,12 +12,10 @@ from .core import ( flatten_config, generate_ansible_yaml, generate_jinja2_template, - generate_puppet_hiera_yaml, - generate_erb_template, ) from .multi import process_directory -from .safety import TemplateSafetyError, verify_erb_template_safe +from .safety import TemplateSafetyError def _build_arg_parser() -> argparse.ArgumentParser: @@ -59,20 +57,6 @@ def _build_arg_parser() -> argparse.ArgumentParser: "--template-output", help="Path to write the generated config template. If omitted, template is printed to stdout.", ) - ap.add_argument( - "--template-engine", - choices=[j2.NAME, "erb"], - default=j2.NAME, - help="Template syntax to generate (default: jinja2). Use erb for Puppet templates.", - ) - ap.add_argument( - "--puppet-class", - help=( - "Puppet class/Hiera namespace to use with --template-engine erb. " - "Defaults to --role-name. This lets tools use a file-specific " - "variable prefix while writing Hiera keys under the real Puppet class." - ), - ) return ap @@ -110,21 +94,7 @@ def _run(argv: list[str] | None = None) -> int: print("# defaults/main.yml") print(defaults_yaml, end="") - # Optionally translate folder-mode templates to ERB. Folder mode keeps - # the existing data shape; single-file mode below is the preferred - # Puppet path because it can produce class-parameter Hiera keys. - if args.template_engine == "erb": - from .erb import translate_jinja2_to_erb - - for o in outputs: - o.template = translate_jinja2_to_erb( - o.template, - role_prefix=args.role_name, - puppet_class=args.puppet_class or args.role_name, - ) - verify_erb_template_safe(o.template) - - template_ext = "erb" if args.template_engine == "erb" else j2.TEMPLATE_EXTENSION + template_ext = j2.TEMPLATE_EXTENSION # Write templates if args.template_output: @@ -161,36 +131,17 @@ def _run(argv: list[str] | None = None) -> int: # Flatten config (excluding loop paths if loops are detected) flat_items = flatten_config(fmt, parsed, loop_candidates) - if args.template_engine == "erb": - ansible_yaml = generate_puppet_hiera_yaml( - args.role_name, - flat_items, - loop_candidates, - puppet_class=args.puppet_class or args.role_name, - ) - template_str = generate_erb_template( - fmt, - parsed, - args.role_name, - original_text=config_text, - loop_candidates=loop_candidates, - flat_items=flat_items, - puppet_class=args.puppet_class or args.role_name, - ) - else: - # Generate defaults YAML (with loop collections if detected) - ansible_yaml = generate_ansible_yaml( - args.role_name, flat_items, loop_candidates - ) + # Generate defaults YAML (with loop collections if detected) + ansible_yaml = generate_ansible_yaml(args.role_name, flat_items, loop_candidates) - # Generate template (with loops if detected) - template_str = generate_jinja2_template( - fmt, - parsed, - args.role_name, - original_text=config_text, - loop_candidates=loop_candidates, - ) + # Generate template (with loops if detected) + template_str = generate_jinja2_template( + fmt, + parsed, + args.role_name, + original_text=config_text, + loop_candidates=loop_candidates, + ) if args.defaults_output: Path(args.defaults_output).write_text(ansible_yaml, encoding="utf-8") @@ -201,11 +152,7 @@ def _run(argv: list[str] | None = None) -> int: if args.template_output: Path(args.template_output).write_text(template_str, encoding="utf-8") else: - print( - "# config.erb" - if args.template_engine == "erb" - else f"# config.{j2.TEMPLATE_EXTENSION}" - ) + print(f"# config.{j2.TEMPLATE_EXTENSION}") print(template_str, end="") return 0 diff --git a/src/jinjaturtle/core.py b/src/jinjaturtle/core.py index 4d35260..8e3d10e 100644 --- a/src/jinjaturtle/core.py +++ b/src/jinjaturtle/core.py @@ -8,9 +8,7 @@ import re import yaml from .loop_analyzer import LoopAnalyzer, LoopCandidate -from .erb import puppet_class_name, puppet_local_var_name, translate_jinja2_to_erb from .safety import ( - verify_erb_template_safe, verify_jinja2_template_safe, ) from .handlers import ( @@ -411,74 +409,6 @@ def _template_variable_names( return names -def generate_puppet_hiera_yaml( - role_prefix: str, - flat_items: list[tuple[tuple[str, ...], Any]], - loop_candidates: list[LoopCandidate] | None = None, - *, - puppet_class: str | None = None, -) -> str: - """Create Puppet Hiera data suitable for Automatic Parameter Lookup. - - ``role_prefix`` remains the source variable prefix used by JinjaTurtle while - ``puppet_class`` is the Puppet class/Hiera namespace. In the normal case - they are the same, so ``php_memory_limit`` becomes ``php::memory_limit``. - """ - - klass = puppet_class_name(puppet_class or role_prefix) - data: dict[str, Any] = {} - - for path, value in flat_items: - generated = make_var_name(role_prefix, path) - local = puppet_local_var_name(role_prefix, generated, puppet_class=klass) - data[f"{klass}::{local}"] = value - - if loop_candidates: - for candidate in loop_candidates: - generated = make_var_name(role_prefix, candidate.path) - local = puppet_local_var_name(role_prefix, generated, puppet_class=klass) - data[f"{klass}::{local}"] = candidate.items - - return dump_yaml(data, sort_keys=True) - - -def generate_erb_template( - fmt: str, - parsed: Any, - role_prefix: str, - *, - original_text: str | None = None, - loop_candidates: list[LoopCandidate] | None = None, - flat_items: list[tuple[tuple[str, ...], Any]] | None = None, - puppet_class: str | None = None, -) -> str: - """Generate a Puppet ERB template from JinjaTurtle's renderer-neutral data. - - The first implementation intentionally translates the Jinja2 subset emitted - by JinjaTurtle's existing format handlers. This keeps parsing, formatting - preservation, and loop detection identical between Jinja2 and ERB output - while still producing Puppet-native ``@parameter`` references. - """ - - jinja_template = generate_jinja2_template( - fmt, - parsed, - role_prefix, - original_text=original_text, - loop_candidates=loop_candidates, - ) - names = _template_variable_names(role_prefix, flat_items or [], loop_candidates) - erb_template = translate_jinja2_to_erb( - jinja_template, - role_prefix=role_prefix, - puppet_class=puppet_class or role_prefix, - variable_names=names, - ) - # Defence in depth: no live Jinja2 delimiter may survive translation. - verify_erb_template_safe(erb_template) - return erb_template - - def _stringify_timestamps(obj: Any) -> Any: """ Recursively walk a parsed config and turn any datetime/date/time objects diff --git a/src/jinjaturtle/erb.py b/src/jinjaturtle/erb.py deleted file mode 100644 index 4da6a6e..0000000 --- a/src/jinjaturtle/erb.py +++ /dev/null @@ -1,243 +0,0 @@ -from __future__ import annotations - -import re - -from .escape import escape_erb_literal - - -def _safe_name(raw: str, *, fallback: str = "var") -> str: - text = re.sub(r"[^A-Za-z0-9_]+", "_", str(raw or fallback)).strip("_").lower() - text = re.sub(r"_+", "_", text) - if not text: - text = fallback - if not re.match(r"^[a-z_]", text): - text = f"{fallback}_{text}" - return text - - -def puppet_class_name(raw: str) -> str: - """Return a conservative Puppet class/Hiera namespace name.""" - - text = _safe_name(raw, fallback="jinjaturtle") - if not re.match(r"^[a-z]", text): - text = f"jinjaturtle_{text}" - return text - - -def _role_prefix_name(raw: str) -> str: - return _safe_name(raw, fallback="jinjaturtle") - - -def puppet_local_var_name( - role_prefix: str, - jinja_var_name: str, - *, - puppet_class: str | None = None, -) -> str: - """Map a generated JinjaTurtle variable to a Puppet class parameter. - - For the common case where ``--role-name php`` also means class ``php``, a - generated Jinja variable such as ``php_memory_limit`` becomes Puppet local - parameter ``memory_limit`` and Hiera key ``php::memory_limit``. - - When ``puppet_class`` differs from ``role_prefix`` we keep the full - generated variable name as the local parameter and only use ``puppet_class`` - as the Hiera namespace. - """ - - var_name = _safe_name(jinja_var_name, fallback="value") - prefix = _role_prefix_name(role_prefix) - klass = puppet_class_name(puppet_class or role_prefix) - if klass == prefix and var_name.startswith(prefix + "_"): - stripped = var_name[len(prefix) + 1 :] - return stripped or var_name - return var_name - - -class ErbTranslator: - """Translate the Jinja2 subset emitted by JinjaTurtle into Puppet ERB.""" - - _TOKEN_RE = re.compile(r"({{.*?}}|{%.*?%})", re.S) - - def __init__( - self, - *, - role_prefix: str, - puppet_class: str | None = None, - variable_names: set[str] | None = None, - ) -> None: - self.role_prefix = role_prefix - self.puppet_class = puppet_class or role_prefix - self.variable_names = set(variable_names or set()) - self.loop_stack: list[tuple[str, str, str]] = [] - self.needs_json = False - - # Matches a JinjaTurtle ``{% raw %} ... {% endraw %}`` block (non-greedy). - # JinjaTurtle emits raw blocks only to carry verbatim, security-escaped - # source text (comments and unrecognised lines), so the *contents* must be - # treated as literal output, never translated as Jinja tokens. - _RAW_BLOCK_RE = re.compile( - r"{%[-+]?\s*raw\s*[-+]?%}(.*?){%[-+]?\s*endraw\s*[-+]?%}", re.S - ) - - def translate(self, template_text: str) -> str: - # Split out raw blocks first. Their inner text is literal and must be - # carried through as literal ERB (with ERB delimiters re-escaped), rather - # than tokenised -- otherwise an escaped Jinja payload inside a comment - # would be "re-animated" into live ERB during translation. - segments = self._RAW_BLOCK_RE.split(template_text) - out: list[str] = [] - # re.split with one capture group yields: [text, raw_inner, text, ...]. - for idx, segment in enumerate(segments): - if idx % 2 == 1: - # Captured raw-block contents: emit as literal ERB text. - out.append(escape_erb_literal(segment)) - else: - out.append(self._translate_tokens(segment)) - - rendered = "".join(out) - if self.needs_json and "require 'json'" not in rendered: - rendered = "<% require 'json' -%>\n" + rendered - return rendered - - def _translate_tokens(self, template_text: str) -> str: - parts = self._TOKEN_RE.split(template_text) - out: list[str] = [] - for token in parts: - if not token: - continue - if token.startswith("{{") and token.endswith("}}"): - expr = token[2:-2].strip() - out.append(f"<%= {self.expr_to_ruby(expr)} %>") - continue - if token.startswith("{%") and token.endswith("%}"): - stmt = token[2:-2].strip() - out.append(self.statement_to_erb(stmt)) - continue - out.append(token) - return "".join(out) - - def local_var(self, name: str) -> str: - return puppet_local_var_name( - self.role_prefix, name, puppet_class=self.puppet_class - ) - - def ruby_value(self, expr: str) -> str: - expr = expr.strip() - if expr in {"true", "True"}: - return "true" - if expr in {"false", "False"}: - return "false" - if expr in {"none", "None", "null"}: - return "nil" - if re.match(r"^[A-Za-z_][A-Za-z0-9_]*$", expr): - if any(expr == loop_var for loop_var, _idx, _coll in self.loop_stack): - return expr - return f"@{self.local_var(expr)}" - m = re.match(r"^([A-Za-z_][A-Za-z0-9_]*)\.([A-Za-z_][A-Za-z0-9_]*)$", expr) - if m: - base, key = m.groups() - if any(base == loop_var for loop_var, _idx, _coll in self.loop_stack): - return f"{base}[{key!r}]" - return f"@{self.local_var(base)}[{key!r}]" - return expr - - def expr_to_ruby(self, expr: str) -> str: - expr = expr.strip() - - # JinjaTurtle emits these YAML-preserving ternaries for booleans/nulls. - m = re.match( - r"^(['\"])(true|false)\1\s+if\s+([A-Za-z_][A-Za-z0-9_\.]*)\s+else\s+(['\"])(true|false)\4$", - expr, - ) - if m: - truthy = m.group(2) - cond = self.ruby_value(m.group(3)) - falsy = m.group(5) - return f"{cond} ? {truthy!r} : {falsy!r}" - - m = re.match( - r"^(['\"])(null)\1\s+if\s+([A-Za-z_][A-Za-z0-9_\.]*)\s+is\s+none\s+else\s+([A-Za-z_][A-Za-z0-9_\.]*)$", - expr, - ) - if m: - value = self.ruby_value(m.group(3)) - fallback = self.ruby_value(m.group(4)) - return f"{value}.nil? ? 'null' : {fallback}" - - if "|" in expr: - base, *filters = [part.strip() for part in expr.split("|")] - ruby = self.ruby_value(base) - for filt in filters: - if filt.startswith("lower"): - ruby = f"{ruby}.to_s.downcase" - elif filt.startswith("to_json") or filt.startswith("tojson"): - self.needs_json = True - if "indent" in filt: - ruby = f"JSON.pretty_generate({ruby})" - else: - ruby = f"JSON.generate({ruby})" - return ruby - - return self.ruby_value(expr) - - def statement_to_erb(self, stmt: str) -> str: - if stmt.endswith(("-", "+")): - stmt = stmt[:-1].rstrip() - - if stmt.startswith("for "): - m = re.match( - r"^for\s+([A-Za-z_][A-Za-z0-9_]*)\s+in\s+([A-Za-z_][A-Za-z0-9_]*)$", - stmt, - ) - if m: - loop_var, collection = m.groups() - idx_var = f"__jt_idx_{len(self.loop_stack)}" - collection_ruby = self.ruby_value(collection) - self.loop_stack.append((loop_var, idx_var, collection_ruby)) - return f"<% {collection_ruby}.each_with_index do |{loop_var}, {idx_var}| -%>" - - if stmt == "endfor": - if self.loop_stack: - self.loop_stack.pop() - return "<% end %>" - - if stmt.startswith("if "): - cond = stmt[3:].strip() - if cond == "not loop.last" and self.loop_stack: - _loop_var, idx_var, collection_ruby = self.loop_stack[-1] - return f"<% if {idx_var} < ({collection_ruby}.length - 1) -%>" - m = re.match(r"^([A-Za-z_][A-Za-z0-9_\.]*)\s+is\s+defined$", cond) - if m: - return f"<% unless {self.ruby_value(m.group(1))}.nil? -%>" - m = re.match(r"^([A-Za-z_][A-Za-z0-9_\.]*)\s+is\s+none$", cond) - if m: - return f"<% if {self.ruby_value(m.group(1))}.nil? -%>" - return f"<% if {self.expr_to_ruby(cond)} -%>" - - if stmt == "else": - return "<% else -%>" - - if stmt.startswith("elif "): - return f"<% elsif {self.expr_to_ruby(stmt[5:].strip())} -%>" - - if stmt == "endif": - return "<% end -%>" - - # Preserve unknown Jinja statements visibly as an ERB comment so the - # generated template does not contain invalid Jinja syntax. - return f"<%# Unsupported JinjaTurtle statement: {stmt} %>" - - -def translate_jinja2_to_erb( - template_text: str, - *, - role_prefix: str, - puppet_class: str | None = None, - variable_names: set[str] | None = None, -) -> str: - return ErbTranslator( - role_prefix=role_prefix, - puppet_class=puppet_class, - variable_names=variable_names, - ).translate(template_text) diff --git a/src/jinjaturtle/escape.py b/src/jinjaturtle/escape.py index 129c08a..e55f416 100644 --- a/src/jinjaturtle/escape.py +++ b/src/jinjaturtle/escape.py @@ -9,7 +9,7 @@ always replaced with ``{{ var }}`` placeholders and parked in the defaults data, so a payload inside a value is inert. Verbatim text is different: if the source contains ``{{ ... }}``, ``{% ... %}`` or ``{# ... #}`` (Jinja2), or ``<%= %>`` / ``<% %>`` (ERB), that text becomes *live template code* in the output and is -executed when Salt/Ansible/Puppet later renders the template. +executed when Ansible later renders the template. Because JinjaTurtle is frequently fed harvested, attacker-influenceable config (hostnames, banners, GECOS-derived comments, "Managed by" notes), this is a @@ -30,14 +30,6 @@ Design notes: Jinja construct. The only way to break out of a raw block is a literal ``{% endraw %}`` in the source, so we defang the token ``endraw`` (in any internal spacing) before wrapping. - * The ERB translator (``erb.py``) is raw-aware: it copies the *contents* of a - JinjaTurtle raw block through as literal ERB text and re-escapes any ERB - delimiters found there. That keeps a Jinja-escaped comment inert after the - Jinja2 -> ERB translation step, instead of the payload being "re-animated" - as ERB. - * ``escape_erb_literal`` exists for completeness / direct ERB emission: it - rewrites each ERB delimiter into an ERB expression that prints the delimiter - characters literally. """ import re @@ -70,11 +62,6 @@ def contains_jinja_markup(text: str) -> bool: return any(m in text for m in _JINJA_MARKERS) -def contains_erb_markup(text: str) -> bool: - """Return True if *text* contains any ERB delimiter.""" - return any(m in text for m in (*_ERB_OPEN_MARKERS, *_ERB_CLOSE_MARKERS)) - - def _defang_endraw(text: str) -> str: """Rewrite any literal ``{% endraw %}`` so it cannot close our raw wrapper. @@ -109,45 +96,3 @@ def escape_jinja_literal(text: str) -> str: if not text or not contains_jinja_markup(text): return text return "{% raw %}" + _defang_endraw(text) + "{% endraw %}" - - -def escape_erb_literal(text: str) -> str: - """Make *text* render as literal characters under a later ERB render. - - ERB has no ``raw`` block, so each opening/closing delimiter is rewritten as - an ERB expression that prints the delimiter literally. Text with no ERB - metacharacters is returned unchanged. - """ - if not text or not contains_erb_markup(text): - return text - - result: list[str] = [] - i = 0 - n = len(text) - while i < n: - matched = None - for marker in (*_ERB_CLOSE_MARKERS, *_ERB_OPEN_MARKERS): - if text.startswith(marker, i): - matched = marker - break - if matched is not None: - escaped = matched.replace("\\", "\\\\").replace('"', '\\"') - result.append('<%= "' + escaped + '" %>') - i += len(matched) - else: - result.append(text[i]) - i += 1 - return "".join(result) - - -def escape_literal(text: str, *, engine: str = "jinja2") -> str: - """Escape verbatim *text* for the target template *engine*. - - ``engine`` is ``"jinja2"`` (default) or ``"erb"``. Unknown engines fall back - to Jinja2 escaping. In JinjaTurtle's pipeline ERB output is produced by - translating Jinja2 output, and the translator is raw-aware, so handlers can - always Jinja-escape and rely on the translator to keep the literal inert. - """ - if engine == "erb": - return escape_erb_literal(text) - return escape_jinja_literal(text) diff --git a/src/jinjaturtle/safety.py b/src/jinjaturtle/safety.py index 07d3b8d..713d49a 100644 --- a/src/jinjaturtle/safety.py +++ b/src/jinjaturtle/safety.py @@ -22,8 +22,8 @@ single global property: The check is positive/allowlist-based, which is the safe direction: unknown constructs are rejected, not ignored. It runs at the single choke points in -``core.py`` (``generate_jinja2_template`` / ``generate_erb_template``), so it -covers every current handler and every future one automatically. +``core.py`` (``generate_jinja2_template``) so it covers every current handler and +every future one automatically. Why this is robust against the escaper being wrong --------------------------------------------------- diff --git a/tests/test_cli.py b/tests/test_cli.py index e4ac519..c0d5470 100644 --- a/tests/test_cli.py +++ b/tests/test_cli.py @@ -132,57 +132,3 @@ def test_cli_folder_single_output_file_when_one_format(tmp_path): assert defaults_path.is_file() assert template_path.is_file() assert "to_json" in template_path.read_text(encoding="utf-8") - - -def test_cli_erb_outputs_puppet_hiera_and_erb_template(tmp_path): - cfg = tmp_path / "app.ini" - cfg.write_text("[main]\nport = 8080\n", encoding="utf-8") - data_out = tmp_path / "common.yaml" - template_out = tmp_path / "app.ini.erb" - - exit_code = cli._main( - [ - str(cfg), - "-r", - "php", - "--template-engine", - "erb", - "--defaults-output", - str(data_out), - "--template-output", - str(template_out), - ] - ) - - assert exit_code == 0 - assert "php::main_port: '8080'" in data_out.read_text(encoding="utf-8") - assert "port = <%= @main_port %>" in template_out.read_text(encoding="utf-8") - - -def test_cli_erb_can_use_separate_puppet_class_namespace(tmp_path): - cfg = tmp_path / "app.ini" - cfg.write_text("[main]\nport = 8080\n", encoding="utf-8") - data_out = tmp_path / "node.yaml" - template_out = tmp_path / "app.ini.erb" - - exit_code = cli._main( - [ - str(cfg), - "-r", - "php_etc_app_ini", - "--template-engine", - "erb", - "--puppet-class", - "php", - "--defaults-output", - str(data_out), - "--template-output", - str(template_out), - ] - ) - - assert exit_code == 0 - data = data_out.read_text(encoding="utf-8") - template = template_out.read_text(encoding="utf-8") - assert "php::php_etc_app_ini_main_port: '8080'" in data - assert "port = <%= @php_etc_app_ini_main_port %>" in template diff --git a/tests/test_injection_security.py b/tests/test_injection_security.py index a1de483..9ff0230 100644 --- a/tests/test_injection_security.py +++ b/tests/test_injection_security.py @@ -3,8 +3,8 @@ JinjaTurtle copies parts of the source config (comments, unrecognised lines, structural keys) verbatim into the generated template. If that text contains Jinja2/ERB delimiters it must be neutralised, otherwise attacker-influenced -config content becomes live template code that executes when Salt/Ansible/Puppet -later renders the template. +config content becomes live template code that executes when Ansible later +renders the template. These tests render the *generated* template the way a downstream tool would and assert that an injected payload never executes. A tripwire object is exposed @@ -14,7 +14,6 @@ the tripwire sentinel, an injected expression executed and the test fails. from __future__ import annotations -import re import subprocess import sys from pathlib import Path @@ -25,8 +24,6 @@ import yaml as pyyaml from jinjaturtle.escape import ( escape_jinja_literal, - escape_erb_literal, - escape_literal, ) TRIP = "__TRIPWIRE_FIRED__" @@ -233,43 +230,3 @@ def test_endraw_whitespace_control_cannot_break_out(endraw): rendered = env.from_string(escaped).render(boom=_Boom()) assert TRIP not in rendered assert rendered == payload - - -@pytest.mark.parametrize( - "payload", - [ - "<%= system('id') %>", - "<% require 'open3' %>", - "text <%= 1+1 %> more", - "-%> orphan <%", - ], -) -def test_escape_erb_literal_removes_executable_tags(payload): - escaped = escape_erb_literal(payload) - # No raw executable ERB tag should survive that contains the original code. - live = re.findall(r"<%[-=#]?(.*?)-?%>", escaped, re.S) - for chunk in live: - assert "system" not in chunk - assert "require" not in chunk - # Numeric/expression payloads must be reduced to literal-string prints. - - -def test_escape_literal_dispatches_by_engine(): - """The public ``escape_literal`` wrapper routes to the right engine.""" - payload = "{{ 7*7 }}" - # Default engine is Jinja2. - assert escape_literal(payload) == escape_jinja_literal(payload) - assert escape_literal(payload, engine="jinja2") == escape_jinja_literal(payload) - # An unknown engine falls back to the safer Jinja2 escaping. - assert escape_literal(payload, engine="nonsense") == escape_jinja_literal(payload) - # ERB routing. - erb_payload = "<%= system('id') %>" - assert escape_literal(erb_payload, engine="erb") == escape_erb_literal(erb_payload) - - -def test_escape_literal_jinja_output_is_inert(): - """End-to-end: text routed through escape_literal does not execute.""" - escaped = escape_literal("{{ boom.run('x') }}") - env = jinja2.Environment(undefined=jinja2.ChainableUndefined) - rendered = env.from_string(escaped).render(boom=_Boom()) - assert TRIP not in rendered diff --git a/tests/test_yaml_handler.py b/tests/test_yaml_handler.py index a217e8a..548f5a6 100644 --- a/tests/test_yaml_handler.py +++ b/tests/test_yaml_handler.py @@ -10,7 +10,6 @@ from jinjaturtle.core import ( analyze_loops, flatten_config, generate_ansible_yaml, - generate_erb_template, generate_jinja2_template, ) from jinjaturtle.handlers.yaml import YamlHandler @@ -205,16 +204,6 @@ def test_yaml_loop_preserves_blank_separator_after_list(tmp_path: Path): rendered = Template(template).render(**defaults) assert rendered_expected in rendered - erb_template = generate_erb_template( - fmt, - parsed, - "role", - original_text=text, - loop_candidates=loop_candidates, - flat_items=flat_items, - ) - assert erb_expected in erb_template - def test_yaml_loop_preserves_following_top_level_comments(tmp_path: Path): from jinja2 import Environment, Template From 4a1f2ac15e2ba51c018e8fed8f9a079c3e5d0539 Mon Sep 17 00:00:00 2001 From: Miguel Jacq Date: Sun, 28 Jun 2026 20:33:12 +1000 Subject: [PATCH 12/25] More JSON defenses --- src/jinjaturtle/core.py | 8 +++ src/jinjaturtle/handlers/json.py | 34 +++++++++++-- src/jinjaturtle/multi.py | 4 +- src/jinjaturtle/safety.py | 84 +++++++++++++++++++++++++++++++- tests/test_injection_security.py | 80 ++++++++++++++++++++++++++++++ 5 files changed, 203 insertions(+), 7 deletions(-) diff --git a/src/jinjaturtle/core.py b/src/jinjaturtle/core.py index 8e3d10e..3e9cefd 100644 --- a/src/jinjaturtle/core.py +++ b/src/jinjaturtle/core.py @@ -10,6 +10,7 @@ import yaml from .loop_analyzer import LoopAnalyzer, LoopCandidate from .safety import ( verify_jinja2_template_safe, + verify_no_live_jinja_in_json_keys, ) from .handlers import ( BaseHandler, @@ -394,6 +395,13 @@ def generate_jinja2_template( # verbatim source text, the un-escaped payload shows up here as a live tag # and generation aborts instead of emitting an injectable template. verify_jinja2_template_safe(template) + + # Format-specific backstop: JinjaTurtle never emits Jinja inside a JSON object + # key, so a live construct in key position means source key text leaked into + # the template unescaped. This is independent of per-handler escaping. + if fmt == "json": + verify_no_live_jinja_in_json_keys(template) + return template diff --git a/src/jinjaturtle/handlers/json.py b/src/jinjaturtle/handlers/json.py index 064535a..0268666 100644 --- a/src/jinjaturtle/handlers/json.py +++ b/src/jinjaturtle/handlers/json.py @@ -7,6 +7,7 @@ from typing import Any from . import DictLikeHandler from .. import j2 +from ..escape import escape_jinja_literal from ..loop_analyzer import LoopCandidate @@ -109,10 +110,18 @@ class JsonHandler(DictLikeHandler): chunks: list[str] = [] pos = 0 for path, start, end in spans: - chunks.append(text[pos:start]) + # Text between scalar values (object keys, structural punctuation, + # whitespace, and any comment-like trailing text) is copied verbatim + # from the source file. Like every other text-emitting handler, this + # verbatim text must be neutralised: if it contains Jinja2 markup it + # would otherwise become live template code at apply time. The value + # itself is replaced with a safe placeholder below. ``escape_jinja_literal`` + # is a no-op on text without Jinja markers, so benign JSON is unchanged + # byte-for-byte and a later render reproduces the original characters. + chunks.append(escape_jinja_literal(text[pos:start])) chunks.append(self._json_value_expr(self.make_var_name(role_prefix, path))) pos = end - chunks.append(text[pos:]) + chunks.append(escape_jinja_literal(text[pos:])) return "".join(chunks) def _collect_json_scalar_spans( @@ -213,7 +222,12 @@ class JsonHandler(DictLikeHandler): def _walk(obj: Any, path: tuple[str, ...] = ()) -> Any: if isinstance(obj, dict): - return {k: _walk(v, path + (str(k),)) for k, v in obj.items()} + # Keys are emitted verbatim into the template, so neutralise any + # Jinja markup in them (see _generate_json_template_from_text). + return { + escape_jinja_literal(str(k)): _walk(v, path + (str(k),)) + for k, v in obj.items() + } if isinstance(obj, list): return [_walk(v, path + (str(i),)) for i, v in enumerate(obj)] # scalar - use marker that will be replaced with to_json @@ -261,7 +275,12 @@ class JsonHandler(DictLikeHandler): return f"__LOOP_DICT__{collection_var}__{item_var}__" if isinstance(obj, dict): - return {k: _walk(v, current_path + (str(k),)) for k, v in obj.items()} + # Keys are emitted verbatim into the template, so neutralise any + # Jinja markup in them (see _generate_json_template_from_text). + return { + escape_jinja_literal(str(k)): _walk(v, current_path + (str(k),)) + for k, v in obj.items() + } if isinstance(obj, list): # Check if this list is a loop candidate if current_path in loop_paths: @@ -364,8 +383,13 @@ class JsonHandler(DictLikeHandler): ] # first line has no indent; we prepend `inner` when emitting for i, key in enumerate(keys): comma = "," if i < len(keys) - 1 else "" + # The literal key text is emitted verbatim into the template; escape any + # Jinja markup in it. The value side ({item_var}.{key}) is constrained by + # the output safety gate's dotted-name allowlist, which fails closed on + # anything that is not a plain identifier path. dict_lines.append( - f'{field}"{key}": ' f"{j2.to_json(f'{item_var}.{key}')}{comma}" + f'{field}"{escape_jinja_literal(str(key))}": ' + f"{j2.to_json(f'{item_var}.{key}')}{comma}" ) # Comma between *items* goes after the closing brace. dict_lines.append(f"{inner}}}{j2.if_not_loop_last()},{j2.endif()}") diff --git a/src/jinjaturtle/multi.py b/src/jinjaturtle/multi.py index 195434f..c945481 100644 --- a/src/jinjaturtle/multi.py +++ b/src/jinjaturtle/multi.py @@ -31,7 +31,7 @@ import xml.etree.ElementTree as ET # nosec from . import j2 from .core import dump_yaml, flatten_config, make_var_name, parse_config from .handlers.xml import XmlHandler -from .safety import verify_jinja2_template_safe +from .safety import verify_jinja2_template_safe, verify_no_live_jinja_in_json_keys from .escape import escape_jinja_literal @@ -784,5 +784,7 @@ def process_directory( # Any un-neutralised source text that became a live tag aborts generation. for out in outputs: verify_jinja2_template_safe(out.template) + if out.fmt == "json": + verify_no_live_jinja_in_json_keys(out.template) return defaults_yaml, outputs diff --git a/src/jinjaturtle/safety.py b/src/jinjaturtle/safety.py index 713d49a..5ed2fe1 100644 --- a/src/jinjaturtle/safety.py +++ b/src/jinjaturtle/safety.py @@ -43,6 +43,7 @@ __all__ = [ "TemplateSafetyError", "verify_jinja2_template_safe", "verify_erb_template_safe", + "verify_no_live_jinja_in_json_keys", ] @@ -208,7 +209,88 @@ def verify_jinja2_template_safe(template_text: str) -> None: # --------------------------------------------------------------------------- # -# ERB gate. +# JSON-key gate (defence in depth, format-specific). +# +# JinjaTurtle never emits a live Jinja construct inside a JSON *object key*: keys +# are copied verbatim from the source and (after escape.py) are wrapped in +# ``{% raw %}`` if they contain markup, so a key never lexes as a live tag. A +# live construct in key position can therefore only mean source key text leaked +# into the template unescaped (the json-handler blind spot). This gate is +# independent of the escaper: it inspects the finished template, replaces every +# *live* Jinja construct with an inert sentinel (raw-wrapped literal text stays +# literal), and rejects any sentinel that lands in a JSON key slot. +# --------------------------------------------------------------------------- # + +# Sentinel byte that cannot occur in normal generated template text. +_LIVE_SENTINEL = "\x00" + +# A JSON key is a double-quoted string immediately followed (after optional +# whitespace) by a colon. We only need to detect a sentinel *inside* such a +# string, so match a quoted run that ends in `":` and look for the sentinel. +_JSON_KEY_RE = re.compile(r'"((?:[^"\\]|\\.)*)"\s*:', re.S) + +_KEY_JINJA_DELIMS = ("{{", "}}", "{%", "%}", "{#", "#}") + + +def _contains_jinja_delim(text: str) -> bool: + """True if *text* contains any Jinja delimiter (live or escaped-literal).""" + return any(d in text for d in _KEY_JINJA_DELIMS) + + +def verify_no_live_jinja_in_json_keys(template_text: str) -> None: + """Reject a JSON template that carries Jinja markup in an object key. + + JinjaTurtle never templates a JSON *object key*: keys come straight from the + source and a key is an identifier/string, never a value placeholder. Any + Jinja in key position therefore means attacker-influenced source key text + reached the template. This gate fails closed on it, independent of whether a + handler left the markup *live* (a raw ``{{ ... }}`` in the key) or *escaped* + it into a ``{% raw %}`` wrapper -- both indicate a key that should never have + contained templating, so generation aborts rather than emitting it. + + Detection is done on the lexer token stream: we reconstruct the document with + every live tag collapsed to a sentinel and every ``{% raw %}``-wrapped region + also marked, then reject a sentinel that lands inside a JSON key string. + """ + import jinja2 + + env = jinja2.Environment(autoescape=True) + try: + tokens = list(env.lex(template_text)) + except jinja2.TemplateSyntaxError as exc: + raise TemplateSafetyError( + f"generated JSON template does not lex as the JinjaTurtle subset: {exc}" + ) from exc + + out: list[str] = [] + in_tag = False + for _lineno, tok_type, value in tokens: + if tok_type in ("variable_begin", "block_begin", "comment_begin"): + # A live construct: collapse to a sentinel so it is detectable if it + # sits in key position. (raw_begin/raw_end are *not* live; the data + # inside a raw block is preserved verbatim below, so an escaped key + # still shows its literal Jinja delimiters to the key check.) + in_tag = True + out.append(_LIVE_SENTINEL) + elif tok_type in ("variable_end", "block_end", "comment_end"): + in_tag = False + elif not in_tag: + # data, whitespace, raw_begin/raw_end markers, and inert raw content. + out.append(value if isinstance(value, str) else str(value)) + + reconstructed = "".join(out) + + for match in _JSON_KEY_RE.finditer(reconstructed): + key_text = match.group(1) + if _LIVE_SENTINEL in key_text or _contains_jinja_delim(key_text): + raise TemplateSafetyError( + "refusing to emit JSON template: Jinja markup appears inside a " + "JSON object key. JinjaTurtle never templates keys, so this " + "indicates attacker-influenced source key text (possible " + "template injection)." + ) + + # # JinjaTurtle's ERB output is produced by translating the (already-verified) # Jinja2 subset, so the Jinja2 gate is the primary guarantee. As an independent diff --git a/tests/test_injection_security.py b/tests/test_injection_security.py index 9ff0230..1110ef1 100644 --- a/tests/test_injection_security.py +++ b/tests/test_injection_security.py @@ -152,6 +152,86 @@ def test_generated_template_is_renderable(tmp_path, fmt, name, body): _render_jinja(template_text, defaults) +# --- JSON object-key injection ------------------------------------------------ +# +# The JSON handler copies the text *between* scalar values (object keys, +# punctuation) verbatim. A key is never a value placeholder, so Jinja markup in a +# key can only come from attacker-influenced source text. The output gate +# (verify_no_live_jinja_in_json_keys) must fail closed on it -- including the +# "benign-looking name" form (e.g. ``{{ ansible_hostname }}``) that the generic +# allowlist would otherwise accept as an ordinary variable reference, and which +# could leak an in-scope variable's value into the rendered config at apply time. + +JSON_KEY_INJECTION_BODIES = [ + # benign-looking variable reference (the residual bypass: passes the generic + # allowlist but must still be rejected in *key* position) + '{ "{{ ansible_hostname }}": "v" }', + # dotted reference (e.g. dumping another host's vars) + '{ "{{ hostvars.localhost }}": 1 }', + # self-referencing a sibling-derived variable name + '{ "{{ role_port }}": "x", "port": 8080 }', + # classic gadget (already rejected historically; kept as a guard) + '{ "{{ cycler.__init__.__globals__ }}": 1 }', + # statement injection in a key + '{ "{% for x in y %}k{% endfor %}": 1 }', + # nested object key + '{ "ok": { "{{ ansible_hostname }}": 2 } }', +] + + +@pytest.mark.parametrize("body", JSON_KEY_INJECTION_BODIES) +def test_json_key_injection_fails_closed_cli(tmp_path, body): + src = tmp_path / "evil.json" + src.write_text(body, encoding="utf-8") + out = tmp_path / "out.j2" + res = subprocess.run( + [ + sys.executable, + "-m", + "jinjaturtle.cli", + str(src), + "-f", + "json", + "--role-name", + "role", + "-t", + str(out), + ], + capture_output=True, + text=True, + ) + assert res.returncode == 2, f"expected fail-closed, got rc={res.returncode}" + assert "refusing to generate unsafe template" in res.stderr + assert not out.exists(), "no template may be written when the gate refuses" + + +def test_json_benign_keys_still_generate(tmp_path): + src = tmp_path / "ok.json" + src.write_text('{ "host": "localhost", "port": 8080 }', encoding="utf-8") + out = tmp_path / "out.j2" + res = subprocess.run( + [ + sys.executable, + "-m", + "jinjaturtle.cli", + str(src), + "-f", + "json", + "--role-name", + "demo", + "-t", + str(out), + ], + capture_output=True, + text=True, + ) + assert res.returncode == 0, res.stderr + template_text = out.read_text() + # Keys stay literal; values become placeholders. + assert '"host":' in template_text + assert "demo_host" in template_text + + # --- Unit-level guarantees for the escaper itself --------------------------- SSTI_PAYLOADS = [ From 70be0f7e33ff04362036dc03d5403b3984201f5b Mon Sep 17 00:00:00 2001 From: Miguel Jacq Date: Mon, 29 Jun 2026 08:51:53 +1000 Subject: [PATCH 13/25] Hardening: use unsafe for ansible vars, ensure API use of JinjaTurtle uses safe XML parsing, avoid symlinks --- src/jinjaturtle/cli.py | 18 +++-- src/jinjaturtle/core.py | 45 ++++++++++- src/jinjaturtle/handlers/xml.py | 13 ++-- src/jinjaturtle/multi.py | 30 +++++++- src/jinjaturtle/output_safety.py | 124 +++++++++++++++++++++++++++++++ tests/test_injection_security.py | 17 ++++- tests/test_security_hardening.py | 120 ++++++++++++++++++++++++++++++ 7 files changed, 348 insertions(+), 19 deletions(-) create mode 100644 src/jinjaturtle/output_safety.py create mode 100644 tests/test_security_hardening.py diff --git a/src/jinjaturtle/cli.py b/src/jinjaturtle/cli.py index 0eaf506..bdabc18 100644 --- a/src/jinjaturtle/cli.py +++ b/src/jinjaturtle/cli.py @@ -16,6 +16,7 @@ from .core import ( from .multi import process_directory from .safety import TemplateSafetyError +from .output_safety import OutputPathError, ensure_safe_directory, write_text_safely def _build_arg_parser() -> argparse.ArgumentParser: @@ -72,6 +73,9 @@ def _main(argv: list[str] | None = None) -> int: f"jinjaturtle: refusing to generate unsafe template: {exc}", file=sys.stderr ) return 2 + except OutputPathError as exc: + print(f"jinjaturtle: refusing unsafe output path: {exc}", file=sys.stderr) + return 2 def _run(argv: list[str] | None = None) -> int: @@ -89,7 +93,7 @@ def _run(argv: list[str] | None = None) -> int: # Write defaults if args.defaults_output: - Path(args.defaults_output).write_text(defaults_yaml, encoding="utf-8") + write_text_safely(Path(args.defaults_output), defaults_yaml) else: print("# defaults/main.yml") print(defaults_yaml, end="") @@ -100,12 +104,12 @@ def _run(argv: list[str] | None = None) -> int: if args.template_output: out_path = Path(args.template_output) if len(outputs) == 1 and not out_path.is_dir(): - out_path.write_text(outputs[0].template, encoding="utf-8") + write_text_safely(out_path, outputs[0].template) else: - out_path.mkdir(parents=True, exist_ok=True) + ensure_safe_directory(out_path) for o in outputs: - (out_path / f"config.{o.fmt}.{template_ext}").write_text( - o.template, encoding="utf-8" + write_text_safely( + out_path / f"config.{o.fmt}.{template_ext}", o.template ) else: for o in outputs: @@ -144,13 +148,13 @@ def _run(argv: list[str] | None = None) -> int: ) if args.defaults_output: - Path(args.defaults_output).write_text(ansible_yaml, encoding="utf-8") + write_text_safely(Path(args.defaults_output), ansible_yaml) else: print("# defaults/main.yml") print(ansible_yaml, end="") if args.template_output: - Path(args.template_output).write_text(template_str, encoding="utf-8") + write_text_safely(Path(args.template_output), template_str) else: print(f"# config.{j2.TEMPLATE_EXTENSION}") print(template_str, end="") diff --git a/src/jinjaturtle/core.py b/src/jinjaturtle/core.py index 3e9cefd..72b42de 100644 --- a/src/jinjaturtle/core.py +++ b/src/jinjaturtle/core.py @@ -33,6 +33,22 @@ class QuotedString(str): pass +class AnsibleUnsafeString(str): + """Marker type emitted with Ansible's !unsafe YAML tag. + + Ansible recursively templates string values by default. Source-derived + config values that contain Jinja delimiters must therefore be marked + unsafe in defaults/main.yml, otherwise a harvested value such as + ``{{ lookup('pipe', 'id') }}`` becomes executable on the Ansible + controller when the generated role is applied. + """ + + pass + + +_JINJA_STARTS = ("{{", "{%", "{#") + + def _fallback_str_representer(dumper: yaml.SafeDumper, data: Any): """ Fallback for objects the dumper doesn't know about. @@ -52,7 +68,33 @@ def _quoted_str_representer(dumper: yaml.SafeDumper, data: QuotedString): return dumper.represent_scalar("tag:yaml.org,2002:str", str(data), style='"') +def _ansible_unsafe_str_representer(dumper: yaml.SafeDumper, data: AnsibleUnsafeString): + return dumper.represent_scalar("!unsafe", str(data), style="'") + + +def _needs_ansible_unsafe(value: str) -> bool: + return any(marker in value for marker in _JINJA_STARTS) + + +def _mark_ansible_unsafe_values(obj: Any) -> Any: + """Recursively mark mapping/list values containing Jinja as !unsafe. + + Mapping keys are intentionally left alone: they are variable names or YAML + structure, not Ansible-templated values. Values nested in folder-mode item + lists, including source-derived ``id`` values, are protected. + """ + + if isinstance(obj, dict): + return {k: _mark_ansible_unsafe_values(v) for k, v in obj.items()} + if isinstance(obj, list): + return [_mark_ansible_unsafe_values(v) for v in obj] + if isinstance(obj, str) and _needs_ansible_unsafe(obj): + return AnsibleUnsafeString(obj) + return obj + + _TurtleDumper.add_representer(QuotedString, _quoted_str_representer) +_TurtleDumper.add_representer(AnsibleUnsafeString, _ansible_unsafe_str_representer) # Use our fallback for any unknown object types _TurtleDumper.add_representer(None, _fallback_str_representer) @@ -84,8 +126,9 @@ def dump_yaml(data: Any, *, sort_keys: bool = True) -> str: This is used by both the single-file and multi-file code paths. """ + safe_data = _mark_ansible_unsafe_values(data) return yaml.dump( - data, + safe_data, Dumper=_TurtleDumper, sort_keys=sort_keys, default_flow_style=False, diff --git a/src/jinjaturtle/handlers/xml.py b/src/jinjaturtle/handlers/xml.py index 9fde3ec..56e3fd7 100644 --- a/src/jinjaturtle/handlers/xml.py +++ b/src/jinjaturtle/handlers/xml.py @@ -3,7 +3,8 @@ from __future__ import annotations from collections import Counter, defaultdict from pathlib import Path from typing import Any -import xml.etree.ElementTree as ET # nosec +import xml.etree.ElementTree as ET # nosec B405 - safe trees only; parsing uses defusedxml +import defusedxml.ElementTree as DET from .base import BaseHandler from .. import j2 @@ -20,11 +21,11 @@ class XmlHandler(BaseHandler): def parse(self, path: Path) -> ET.Element: text = path.read_text(encoding="utf-8") - parser = ET.XMLParser( - target=ET.TreeBuilder(insert_comments=False) - ) # nosec B314 - parser.feed(text) - root = parser.close() + # Security must live in the handler, not only in the CLI entry point: + # callers may import JinjaTurtle as a library and invoke parse_config() + # directly. defusedxml rejects DTD/entity abuse and also discards + # comments by default, matching the previous TreeBuilder behaviour. + root = DET.fromstring(text) return root def flatten(self, parsed: Any) -> list[tuple[tuple[str, ...], Any]]: diff --git a/src/jinjaturtle/multi.py b/src/jinjaturtle/multi.py index c945481..c968d61 100644 --- a/src/jinjaturtle/multi.py +++ b/src/jinjaturtle/multi.py @@ -22,7 +22,9 @@ Notes: from collections import Counter, defaultdict from copy import deepcopy +import os import configparser +import stat from dataclasses import dataclass from pathlib import Path from typing import Any, Iterable @@ -44,8 +46,23 @@ SUPPORTED_SUFFIXES: dict[str, set[str]] = { } +def _lstat(path: Path) -> os.stat_result: + return path.lstat() + + def is_supported_file(path: Path) -> bool: - if not path.is_file(): + """Return True only for real regular files with supported suffixes. + + pathlib.Path.is_file() follows symlinks. Folder mode must not follow + attacker-controlled symlinks when run over an untrusted tree, especially if + an administrator accidentally runs the CLI as root. + """ + + try: + st = _lstat(path) + except FileNotFoundError: + return False + if not stat.S_ISREG(st.st_mode): return False suffix = path.suffix.lower() for exts in SUPPORTED_SUFFIXES.values(): @@ -55,11 +72,16 @@ def is_supported_file(path: Path) -> bool: def iter_supported_files(root: Path, recursive: bool) -> list[Path]: - if not root.exists(): + try: + st = _lstat(root) + except FileNotFoundError: raise FileNotFoundError(str(root)) - if root.is_file(): + + if stat.S_ISLNK(st.st_mode): + raise ValueError(f"refusing to follow symlink: {root}") + if stat.S_ISREG(st.st_mode): return [root] if is_supported_file(root) else [] - if not root.is_dir(): + if not stat.S_ISDIR(st.st_mode): return [] it = root.rglob("*") if recursive else root.glob("*") diff --git a/src/jinjaturtle/output_safety.py b/src/jinjaturtle/output_safety.py new file mode 100644 index 0000000..9833cde --- /dev/null +++ b/src/jinjaturtle/output_safety.py @@ -0,0 +1,124 @@ +from __future__ import annotations + +"""Safer file-output helpers for the JinjaTurtle CLI. + +The CLI is often used by administrators. A plain Path.write_text() follows a +final-path symlink and can therefore be dangerous when a root-run invocation +writes into an attacker-writable tree. These helpers validate path components, +write through a private temporary file in the target directory, and replace the +final path atomically. Existing final-path symlinks are refused rather than +followed. +""" + +import os +from pathlib import Path +import stat +import tempfile + + +class OutputPathError(OSError): + """Raised when a requested output path is unsafe.""" + + +def _absolute(path: Path) -> Path: + return path if path.is_absolute() else Path.cwd() / path + + +def _check_existing_path_not_symlink(path: Path) -> None: + try: + st = path.lstat() + except FileNotFoundError: + return + if stat.S_ISLNK(st.st_mode): + raise OutputPathError(f"refusing to use symlink path: {path}") + + +def _check_existing_output_file(path: Path) -> None: + try: + st = path.lstat() + except FileNotFoundError: + return + if stat.S_ISLNK(st.st_mode): + raise OutputPathError(f"refusing to write through symlink: {path}") + if not stat.S_ISREG(st.st_mode): + raise OutputPathError(f"refusing to replace non-regular file: {path}") + + +def _check_parent_components(parent: Path) -> None: + """Require every existing parent component to be a real directory.""" + + parent = _absolute(parent) + parts = parent.parts + if not parts: + return + + cur = Path(parts[0]) + for part in parts[1:]: + cur = cur / part + try: + st = cur.lstat() + except FileNotFoundError as exc: + raise OutputPathError(f"output parent does not exist: {cur}") from exc + if stat.S_ISLNK(st.st_mode): + raise OutputPathError(f"refusing to use symlink parent: {cur}") + if not stat.S_ISDIR(st.st_mode): + raise OutputPathError(f"output parent is not a directory: {cur}") + + +def ensure_safe_directory(path: Path) -> None: + """Create or validate a directory tree without accepting symlinks.""" + + path = _absolute(path) + parts = path.parts + if not parts: + return + + cur = Path(parts[0]) + for part in parts[1:]: + cur = cur / part + try: + st = cur.lstat() + except FileNotFoundError: + cur.mkdir(mode=0o700) + st = cur.lstat() + if stat.S_ISLNK(st.st_mode): + raise OutputPathError(f"refusing to use symlink directory: {cur}") + if not stat.S_ISDIR(st.st_mode): + raise OutputPathError(f"output path is not a directory: {cur}") + + +def write_text_safely(path: Path, text: str, *, encoding: str = "utf-8") -> None: + """Write text without following a final-path symlink. + + The target's parent must already exist and every parent component must be a + real directory. The write is completed with os.replace(), which atomically + swaps the final directory entry and does not dereference a final symlink. + """ + + path = _absolute(path) + _check_parent_components(path.parent) + _check_existing_output_file(path) + + fd = -1 + tmp_name: str | None = None + try: + fd, tmp_name = tempfile.mkstemp( + prefix=f".{path.name}.", suffix=".tmp", dir=str(path.parent), text=True + ) + with os.fdopen(fd, "w", encoding=encoding) as f: + fd = -1 + f.write(text) + f.flush() + os.fsync(f.fileno()) + os.chmod(tmp_name, 0o600) + _check_existing_output_file(path) + os.replace(tmp_name, path) + tmp_name = None + finally: + if fd >= 0: + os.close(fd) + if tmp_name is not None: + try: + os.unlink(tmp_name) + except FileNotFoundError: + pass diff --git a/tests/test_injection_security.py b/tests/test_injection_security.py index 1110ef1..4afb7a5 100644 --- a/tests/test_injection_security.py +++ b/tests/test_injection_security.py @@ -29,6 +29,21 @@ from jinjaturtle.escape import ( TRIP = "__TRIPWIRE_FIRED__" +class _UnsafeAwareLoader(pyyaml.SafeLoader): + pass + + +def _construct_unsafe(loader: _UnsafeAwareLoader, node: pyyaml.Node): + return loader.construct_scalar(node) + + +_UnsafeAwareLoader.add_constructor("!unsafe", _construct_unsafe) + + +def _safe_load_defaults(text: str): + return pyyaml.load(text, Loader=_UnsafeAwareLoader) + + class _Boom: """Returns the tripwire sentinel for any access/call an SSTI payload makes.""" @@ -82,7 +97,7 @@ def _run_jinjaturtle(tmp_path: Path, source_name: str, body: str, fmt: str): text=True, ) assert res.returncode == 0, f"generation failed: {res.stderr}" - defaults = pyyaml.safe_load(dfl.read_text()) or {} + defaults = _safe_load_defaults(dfl.read_text()) or {} return tpl.read_text(), defaults diff --git a/tests/test_security_hardening.py b/tests/test_security_hardening.py new file mode 100644 index 0000000..41a6b05 --- /dev/null +++ b/tests/test_security_hardening.py @@ -0,0 +1,120 @@ +from __future__ import annotations + +from pathlib import Path +import os + +import pytest +import yaml +from defusedxml.common import EntitiesForbidden + +from jinjaturtle import cli +from jinjaturtle.core import generate_ansible_yaml, parse_config, flatten_config +from jinjaturtle.multi import is_supported_file, iter_supported_files, process_directory +from jinjaturtle.output_safety import OutputPathError, write_text_safely + + +class UnsafeAwareLoader(yaml.SafeLoader): + pass + + +def _unsafe(loader: UnsafeAwareLoader, node: yaml.Node): + return loader.construct_scalar(node) + + +UnsafeAwareLoader.add_constructor("!unsafe", _unsafe) + + +def test_jinja_values_are_emitted_as_ansible_unsafe(tmp_path: Path): + src = tmp_path / "app.ini" + src.write_text("[main]\ncmd = {{ lookup('pipe','id') }}\n", encoding="utf-8") + + fmt, parsed = parse_config(src) + defaults_yaml = generate_ansible_yaml("role", flatten_config(fmt, parsed)) + + assert "role_main_cmd: !unsafe" in defaults_yaml + assert "{{ lookup(''pipe'',''id'') }}" in defaults_yaml + loaded = yaml.load(defaults_yaml, Loader=UnsafeAwareLoader) + assert loaded["role_main_cmd"] == "{{ lookup('pipe','id') }}" + + +def test_folder_mode_marks_nested_jinja_values_and_ids_unsafe(tmp_path: Path): + src = tmp_path / "src" + src.mkdir() + # Filename ids are source-derived values too. + (src / "{{ bad }}.yaml").write_text( + "message: \"{{ lookup('pipe','id') }}\"\n", encoding="utf-8" + ) + + defaults_yaml, _outputs = process_directory( + src, recursive=False, role_prefix="role" + ) + + assert "id: !unsafe" in defaults_yaml + assert "role_message: !unsafe" in defaults_yaml + loaded = yaml.load(defaults_yaml, Loader=UnsafeAwareLoader) + assert loaded["role_items"][0]["id"] == "{{ bad }}.yaml" + assert loaded["role_items"][0]["role_message"] == "{{ lookup('pipe','id') }}" + + +def test_xml_parser_rejects_entities_when_called_as_library(tmp_path: Path): + src = tmp_path / "bad.xml" + src.write_text( + "]>&xxe;", + encoding="utf-8", + ) + + with pytest.raises(EntitiesForbidden): + parse_config(src, "xml") + + +def test_folder_mode_does_not_follow_symlinked_files(tmp_path: Path): + real = tmp_path / "secret.ini" + real.write_text("[main]\nsecret=yes\n", encoding="utf-8") + root = tmp_path / "root" + root.mkdir() + link = root / "link.ini" + link.symlink_to(real) + + assert not is_supported_file(link) + assert iter_supported_files(root, recursive=False) == [] + assert iter_supported_files(root, recursive=True) == [] + + +@pytest.mark.skipif(not hasattr(os, "symlink"), reason="symlinks unavailable") +def test_cli_refuses_to_write_through_final_symlink(tmp_path: Path): + target = tmp_path / "target.txt" + target.write_text("keep\n", encoding="utf-8") + link = tmp_path / "out.yml" + link.symlink_to(target) + + with pytest.raises(OutputPathError): + write_text_safely(link, "replace\n") + + assert target.read_text(encoding="utf-8") == "keep\n" + assert link.is_symlink() + + +def test_cli_refuses_symlinked_output_parent(tmp_path: Path): + real_dir = tmp_path / "real" + real_dir.mkdir() + link_dir = tmp_path / "linkdir" + link_dir.symlink_to(real_dir, target_is_directory=True) + + with pytest.raises(OutputPathError): + write_text_safely(link_dir / "out.yml", "data\n") + + assert not (real_dir / "out.yml").exists() + + +def test_cli_reports_unsafe_output_path_without_overwriting_symlink(tmp_path: Path): + cfg = tmp_path / "app.ini" + cfg.write_text("[main]\nname = ok\n", encoding="utf-8") + target = tmp_path / "target.yml" + target.write_text("keep\n", encoding="utf-8") + link = tmp_path / "defaults.yml" + link.symlink_to(target) + + exit_code = cli._main([str(cfg), "--defaults-output", str(link)]) + + assert exit_code == 2 + assert target.read_text(encoding="utf-8") == "keep\n" From 0e052a073a93ccf45414ef501dc9a49017c3bbf7 Mon Sep 17 00:00:00 2001 From: Miguel Jacq Date: Mon, 29 Jun 2026 14:30:46 +1000 Subject: [PATCH 14/25] Harden output --- src/jinjaturtle/output_safety.py | 165 ++++++++++++++++++++++--------- tests/test_security_hardening.py | 16 +++ 2 files changed, 132 insertions(+), 49 deletions(-) diff --git a/src/jinjaturtle/output_safety.py b/src/jinjaturtle/output_safety.py index 9833cde..eac40f9 100644 --- a/src/jinjaturtle/output_safety.py +++ b/src/jinjaturtle/output_safety.py @@ -2,11 +2,12 @@ from __future__ import annotations """Safer file-output helpers for the JinjaTurtle CLI. -The CLI is often used by administrators. A plain Path.write_text() follows a +The CLI is often used by administrators. A plain Path.write_text() follows a final-path symlink and can therefore be dangerous when a root-run invocation -writes into an attacker-writable tree. These helpers validate path components, -write through a private temporary file in the target directory, and replace the -final path atomically. Existing final-path symlinks are refused rather than +writes into an attacker-writable tree. These helpers validate path components, +refuse symlink parents, reject root-run output through untrusted parent +components, write through a temporary file in the target directory, and replace +the final path atomically. Existing final-path symlinks are refused rather than followed. """ @@ -20,17 +21,111 @@ class OutputPathError(OSError): """Raised when a requested output path is unsafe.""" +# Keep a reference to the real euid getter. Tests can monkeypatch +# _effective_uid directly without changing process-wide os.geteuid behaviour. +_OS_GETEUID = getattr(os, "geteuid", None) + + +def _effective_uid() -> int | None: + if _OS_GETEUID is None: + return None + try: + return int(_OS_GETEUID()) + except OSError: + return None + + def _absolute(path: Path) -> Path: - return path if path.is_absolute() else Path.cwd() / path + expanded = path.expanduser() + return expanded if expanded.is_absolute() else Path.cwd() / expanded -def _check_existing_path_not_symlink(path: Path) -> None: +def _chmod_private(path: Path) -> None: + try: + os.chmod(path, 0o700) + except OSError: + # Best-effort; mkdir(mode=0o700) is already used for normal filesystems. + pass + + +def _assert_trusted_root_parent(path: Path, st: os.stat_result) -> None: + """Reject root-run output through attacker-controlled parent directories. + + A root-run JinjaTurtle process may write files that an administrator later + applies as configuration-management input. Parent directories controlled by + an unprivileged user are therefore not acceptable output anchors. Root-owned + sticky shared directories such as /tmp are allowed as a boundary, but any + existing child below them must be root-owned and not writable by group/other. + """ + + if _effective_uid() != 0: + return + if not stat.S_ISDIR(st.st_mode): + raise OutputPathError(f"output parent is not a directory: {path}") + if st.st_uid != 0: + raise OutputPathError( + f"output parent is not owned by root; refusing root-run output: {path}" + ) + writable_by_group_or_other = st.st_mode & (stat.S_IWGRP | stat.S_IWOTH) + sticky = st.st_mode & stat.S_ISVTX + if writable_by_group_or_other and not sticky: + raise OutputPathError( + "output parent is writable by group/other; " + f"refusing root-run output: {path}" + ) + + +def _assert_existing_directory_component(path: Path) -> None: try: st = path.lstat() - except FileNotFoundError: - return + except OSError as exc: + raise OutputPathError(f"unable to inspect output parent: {path}") from exc if stat.S_ISLNK(st.st_mode): - raise OutputPathError(f"refusing to use symlink path: {path}") + raise OutputPathError(f"refusing to use symlink parent: {path}") + if not stat.S_ISDIR(st.st_mode): + raise OutputPathError(f"output parent is not a directory: {path}") + _assert_trusted_root_parent(path, st) + + +def _mkdir_safe_dir_tree(path: Path) -> Path: + """Create/validate a directory tree one component at a time. + + pathlib.mkdir(parents=True) can traverse a symlink inserted after a parent + pre-check. Walking one component at a time keeps every existing component + checked before it is used, and newly-created components are immediately + re-inspected. + """ + + out = _absolute(path) + parts = out.parts + if not parts: + return out + + if out.is_absolute(): + cur = Path(parts[0]) + rest = parts[1:] + _assert_existing_directory_component(cur) + else: + # _absolute() currently always returns an absolute path, but keep this + # branch for clarity if that helper is ever relaxed. + cur = Path.cwd() + rest = parts + _assert_existing_directory_component(cur) + + for part in rest: + cur = cur / part + if os.path.lexists(cur): + _assert_existing_directory_component(cur) + continue + try: + os.mkdir(cur, 0o700) + except FileExistsError: + _assert_existing_directory_component(cur) + continue + _chmod_private(cur) + _assert_existing_directory_component(cur) + + return out def _check_existing_output_file(path: Path) -> None: @@ -45,65 +140,36 @@ def _check_existing_output_file(path: Path) -> None: def _check_parent_components(parent: Path) -> None: - """Require every existing parent component to be a real directory.""" + """Require every existing parent component to be a trusted real directory.""" - parent = _absolute(parent) - parts = parent.parts - if not parts: - return - - cur = Path(parts[0]) - for part in parts[1:]: - cur = cur / part - try: - st = cur.lstat() - except FileNotFoundError as exc: - raise OutputPathError(f"output parent does not exist: {cur}") from exc - if stat.S_ISLNK(st.st_mode): - raise OutputPathError(f"refusing to use symlink parent: {cur}") - if not stat.S_ISDIR(st.st_mode): - raise OutputPathError(f"output parent is not a directory: {cur}") + _mkdir_safe_dir_tree(parent) def ensure_safe_directory(path: Path) -> None: - """Create or validate a directory tree without accepting symlinks.""" + """Create or validate a directory tree without accepting unsafe parents.""" - path = _absolute(path) - parts = path.parts - if not parts: - return - - cur = Path(parts[0]) - for part in parts[1:]: - cur = cur / part - try: - st = cur.lstat() - except FileNotFoundError: - cur.mkdir(mode=0o700) - st = cur.lstat() - if stat.S_ISLNK(st.st_mode): - raise OutputPathError(f"refusing to use symlink directory: {cur}") - if not stat.S_ISDIR(st.st_mode): - raise OutputPathError(f"output path is not a directory: {cur}") + _mkdir_safe_dir_tree(path) def write_text_safely(path: Path, text: str, *, encoding: str = "utf-8") -> None: """Write text without following a final-path symlink. - The target's parent must already exist and every parent component must be a - real directory. The write is completed with os.replace(), which atomically - swaps the final directory entry and does not dereference a final symlink. + The target's parent is created/validated component by component. Existing + parent symlinks are refused for every user. When running as root, existing + parent components must also be root-owned and not writable by group/other, + except for sticky shared boundaries such as /tmp. Existing final-path + symlinks are refused rather than followed. """ path = _absolute(path) - _check_parent_components(path.parent) + parent = _mkdir_safe_dir_tree(path.parent) _check_existing_output_file(path) fd = -1 tmp_name: str | None = None try: fd, tmp_name = tempfile.mkstemp( - prefix=f".{path.name}.", suffix=".tmp", dir=str(path.parent), text=True + prefix=f".{path.name}.", suffix=".tmp", dir=str(parent), text=True ) with os.fdopen(fd, "w", encoding=encoding) as f: fd = -1 @@ -111,6 +177,7 @@ def write_text_safely(path: Path, text: str, *, encoding: str = "utf-8") -> None f.flush() os.fsync(f.fileno()) os.chmod(tmp_name, 0o600) + _check_parent_components(path.parent) _check_existing_output_file(path) os.replace(tmp_name, path) tmp_name = None diff --git a/tests/test_security_hardening.py b/tests/test_security_hardening.py index 41a6b05..b5bb855 100644 --- a/tests/test_security_hardening.py +++ b/tests/test_security_hardening.py @@ -118,3 +118,19 @@ def test_cli_reports_unsafe_output_path_without_overwriting_symlink(tmp_path: Pa assert exit_code == 2 assert target.read_text(encoding="utf-8") == "keep\n" + + +def test_cli_refuses_root_output_through_group_writable_parent( + tmp_path: Path, monkeypatch +): + from jinjaturtle import output_safety + + unsafe_dir = tmp_path / "unsafe" + unsafe_dir.mkdir() + unsafe_dir.chmod(0o777) + monkeypatch.setattr(output_safety, "_effective_uid", lambda: 0) + + with pytest.raises(OutputPathError): + write_text_safely(unsafe_dir / "out.yml", "data\n") + + assert not (unsafe_dir / "out.yml").exists() From bc4af135b4bb12aa6ddc381d2e63a853e71ee920 Mon Sep 17 00:00:00 2001 From: Miguel Jacq Date: Mon, 29 Jun 2026 14:31:39 +1000 Subject: [PATCH 15/25] Fix tests --- src/jinjaturtle/core.py | 12 ------------ src/jinjaturtle/j2.py | 1 - tests/test_yaml_handler.py | 2 +- 3 files changed, 1 insertion(+), 14 deletions(-) diff --git a/src/jinjaturtle/core.py b/src/jinjaturtle/core.py index 72b42de..d86992b 100644 --- a/src/jinjaturtle/core.py +++ b/src/jinjaturtle/core.py @@ -448,18 +448,6 @@ def generate_jinja2_template( return template -def _template_variable_names( - role_prefix: str, - flat_items: list[tuple[tuple[str, ...], Any]], - loop_candidates: list[LoopCandidate] | None = None, -) -> set[str]: - names = {make_var_name(role_prefix, path) for path, _value in flat_items} - if loop_candidates: - for candidate in loop_candidates: - names.add(make_var_name(role_prefix, candidate.path)) - return names - - def _stringify_timestamps(obj: Any) -> Any: """ Recursively walk a parsed config and turn any datetime/date/time objects diff --git a/src/jinjaturtle/j2.py b/src/jinjaturtle/j2.py index 13531f5..e20ed20 100644 --- a/src/jinjaturtle/j2.py +++ b/src/jinjaturtle/j2.py @@ -2,7 +2,6 @@ from __future__ import annotations from typing import Any -NAME = "jinja2" TEMPLATE_EXTENSION = "j2" JSON_VALUE_FILTER = "to_json(ensure_ascii=False)" diff --git a/tests/test_yaml_handler.py b/tests/test_yaml_handler.py index 548f5a6..a41baf4 100644 --- a/tests/test_yaml_handler.py +++ b/tests/test_yaml_handler.py @@ -187,7 +187,7 @@ def test_yaml_loop_preserves_blank_separator_after_list(tmp_path: Path): ), ] - for label, text, rendered_expected, erb_expected in cases: + for label, text, rendered_expected in cases: path = tmp_path / f"{label}.yml" path.write_text(text, encoding="utf-8") From 5ae85ad11e99b316a4d6e5cb3d81b8cd9aa15c62 Mon Sep 17 00:00:00 2001 From: Miguel Jacq Date: Mon, 29 Jun 2026 14:44:39 +1000 Subject: [PATCH 16/25] Fix tests --- tests/test_yaml_handler.py | 2 -- 1 file changed, 2 deletions(-) diff --git a/tests/test_yaml_handler.py b/tests/test_yaml_handler.py index a41baf4..543c759 100644 --- a/tests/test_yaml_handler.py +++ b/tests/test_yaml_handler.py @@ -177,13 +177,11 @@ def test_yaml_loop_preserves_blank_separator_after_list(tmp_path: Path): "blank", "require:\n - rubocop-performance\n - rubocop-rspec\n\nAllCops:\n NewCops: enable\n", "\n - rubocop-rspec\n\nAllCops:", - "<% end %>\nAllCops:", ), ( "no_blank", "require:\n - rubocop-performance\n - rubocop-rspec\nAllCops:\n NewCops: enable\n", "\n - rubocop-rspec\nAllCops:", - "<% end %>AllCops:", ), ] From 3573e8e7501c6a888732bc5f812f4bc12f93e8bc Mon Sep 17 00:00:00 2001 From: Miguel Jacq Date: Mon, 29 Jun 2026 20:46:07 +1000 Subject: [PATCH 17/25] Make var name collapse underscores --- src/jinjaturtle/handlers/base.py | 19 +++++++++++++-- tests/test_core_utils.py | 40 ++++++++++++++++++++++++++++++++ 2 files changed, 57 insertions(+), 2 deletions(-) diff --git a/src/jinjaturtle/handlers/base.py b/src/jinjaturtle/handlers/base.py index 14aaec7..6be91f0 100644 --- a/src/jinjaturtle/handlers/base.py +++ b/src/jinjaturtle/handlers/base.py @@ -1,5 +1,6 @@ from __future__ import annotations +import re from pathlib import Path from typing import Any, Iterable @@ -57,8 +58,20 @@ class BaseHandler: role_prefix_section_subsection_key Sanitises parts to lowercase [a-z0-9_] and strips extras. + + Consecutive separators are collapsed to a single underscore. This is + required for correctness, not just aesthetics: a source key such as + ``log..level`` or ``cache--size`` would otherwise sanitise to a name + containing a double underscore (``log__level``). The output safety gate + in ``safety.py`` deliberately rejects *any* ``__`` in a generated + identifier because ``__`` is the gateway to every Jinja2 SSTI gadget + (``__class__``/``__globals__``/...). Emitting a dunder here would make + JinjaTurtle's own gate reject JinjaTurtle's own placeholder, aborting + generation on entirely benign config. Collapsing runs keeps every + generated name a plain single-underscore-delimited identifier that the + gate accepts. """ - role_prefix = role_prefix.strip().lower() + role_prefix = re.sub(r"_+", "_", role_prefix.strip().lower()) clean_parts: list[str] = [] for part in path: @@ -70,7 +83,9 @@ class BaseHandler: cleaned_chars.append(c.lower()) else: cleaned_chars.append("_") - cleaned_part = "".join(cleaned_chars).strip("_") + # Collapse runs of underscores (from adjacent separators) to a + # single "_" so the result can never contain a forbidden "__". + cleaned_part = re.sub(r"_+", "_", "".join(cleaned_chars)).strip("_") if cleaned_part: clean_parts.append(cleaned_part) diff --git a/tests/test_core_utils.py b/tests/test_core_utils.py index c8e41e1..fda6dd0 100644 --- a/tests/test_core_utils.py +++ b/tests/test_core_utils.py @@ -191,3 +191,43 @@ def test_flatten_config_unsupported_format(): flatten_config("bogusfmt", parsed=None) assert "Unsupported format" in str(exc.value) + + +def test_make_var_name_collapses_adjacent_separators(): + """Regression: adjacent separators must not produce a forbidden ``__``. + + A source key such as ``log..level`` or ``cache--size`` previously sanitised + to a name containing a double underscore (``..._log__level``). The output + safety gate in safety.py rejects *any* ``__`` in a generated identifier + (it is the gateway to Jinja2 SSTI gadgets), so emitting one made JinjaTurtle + reject its own placeholder and abort generation on entirely benign config. + make_var_name now collapses runs of underscores to a single ``_``. + """ + for raw_key in ("log..level", "cache--size", "a...b", "x.-.y", "a..b--c"): + name = make_var_name("role", ("main", raw_key)) + assert "__" not in name, f"{raw_key!r} produced {name!r}" + # Still a valid Ansible/Jinja identifier. + assert name.replace("_", "").isalnum() or name == "role" + + # The double-underscore-free collapse is stable and predictable. + assert make_var_name("role", ("main", "log..level")) == "role_main_log_level" + assert make_var_name("role", ("main", "cache--size")) == "role_main_cache_size" + # A leading-digit-free prefix with its own repeated separators is collapsed too. + assert make_var_name("My__Role", ("k",)) == "my_role_k" + + +def test_make_var_name_collapsed_names_pass_output_safety_gate(): + """The names make_var_name emits must be accepted by the safety gate. + + This binds the two modules together: whatever identifier make_var_name + produces for a hostile-looking key must lex as the JinjaTurtle subset, so a + real template built from it is not refused. + """ + from jinjaturtle.safety import verify_jinja2_template_safe + + for raw_key in ("log..level", "cache--size", "a...b", "weird..key..name"): + var = make_var_name("demo", ("section", raw_key)) + # Build the kind of expression a handler would emit for this variable. + template = "{{ " + var + " }}" + # Must not raise TemplateSafetyError. + verify_jinja2_template_safe(template) From 42321a8ec97918853aeb1fe6d438b5bb836703ca Mon Sep 17 00:00:00 2001 From: Miguel Jacq Date: Mon, 29 Jun 2026 20:47:05 +1000 Subject: [PATCH 18/25] Catch malformed config errors gracefully --- src/jinjaturtle/cli.py | 7 ++ src/jinjaturtle/core.py | 79 ++++++++++++++++++- src/jinjaturtle/multi.py | 17 ++++- tests/test_config_parse_errors.py | 123 ++++++++++++++++++++++++++++++ 4 files changed, 223 insertions(+), 3 deletions(-) create mode 100644 tests/test_config_parse_errors.py diff --git a/src/jinjaturtle/cli.py b/src/jinjaturtle/cli.py index bdabc18..65dfa72 100644 --- a/src/jinjaturtle/cli.py +++ b/src/jinjaturtle/cli.py @@ -12,6 +12,7 @@ from .core import ( flatten_config, generate_ansible_yaml, generate_jinja2_template, + ConfigParseError, ) from .multi import process_directory @@ -76,6 +77,12 @@ def _main(argv: list[str] | None = None) -> int: except OutputPathError as exc: print(f"jinjaturtle: refusing unsafe output path: {exc}", file=sys.stderr) return 2 + except ConfigParseError as exc: + # The source file could not be parsed as its (detected or forced) + # format. This is expected for malformed/attacker-influenced input; + # fail cleanly with a non-zero exit code instead of a traceback. + print(f"jinjaturtle: {exc}", file=sys.stderr) + return 1 def _run(argv: list[str] | None = None) -> int: diff --git a/src/jinjaturtle/core.py b/src/jinjaturtle/core.py index d86992b..de34735 100644 --- a/src/jinjaturtle/core.py +++ b/src/jinjaturtle/core.py @@ -305,6 +305,66 @@ def detect_format(path: Path, explicit: str | None = None) -> str: return "ini" +class ConfigParseError(Exception): + """Raised when a source config file cannot be parsed as its format. + + Each underlying parser (json, tomllib, PyYAML, defusedxml/ElementTree, + configparser) raises its own exception type on malformed input. Without a + single normalised error, a malformed file -- which is entirely expected when + JinjaTurtle is pointed at harvested, attacker-influenceable config -- would + escape as an unhandled traceback (e.g. ``xml.etree.ElementTree.ParseError`` + on an XML file whose element name is not well-formed). ``parse_config`` + converts every such failure into this one type so the CLI can fail closed + with a clean message and a non-zero exit code, and so library callers (such + as Enroll, which falls back to copying the raw file) have a single, stable + exception to catch. + + Note: defusedxml's *security* exceptions (``EntitiesForbidden``, + ``DTDForbidden``, ...) are intentionally NOT folded into this type. They + signal an attempted XXE/entity-expansion attack rather than a benign + malformed file, and must propagate unchanged so callers can tell the two + apart. + """ + + +def _build_malformed_config_errors() -> tuple[type[BaseException], ...]: + """Return the concrete "this file is malformed" exception types to catch. + + Deliberately specific. In particular we must avoid catching plain + ``ValueError``: defusedxml's ``EntitiesForbidden``/``DTDForbidden`` subclass + ``ValueError``, and those are security signals that must NOT be swallowed. + """ + + import configparser + import json + from xml.etree.ElementTree import ParseError as _XMLParseError # nosec + + import yaml as _yaml + + errs: list[type[BaseException]] = [ + _XMLParseError, + json.JSONDecodeError, + configparser.Error, + _yaml.YAMLError, + UnicodeDecodeError, + ] + try: + import tomllib + + errs.append(tomllib.TOMLDecodeError) + except ModuleNotFoundError: # pragma: no cover - Python < 3.11 fallback + try: + import tomli # type: ignore + + errs.append(tomli.TOMLDecodeError) + except ModuleNotFoundError: + pass + return tuple(errs) + + +_MALFORMED_CONFIG_ERRORS = _build_malformed_config_errors() + + def parse_config(path: Path, fmt: str | None = None) -> tuple[str, Any]: """ Parse config file into a Python object. @@ -313,7 +373,24 @@ def parse_config(path: Path, fmt: str | None = None) -> tuple[str, Any]: handler = _HANDLERS.get(fmt) if handler is None: raise ValueError(f"Unsupported config format: {fmt}") - parsed = handler.parse(path) + try: + parsed = handler.parse(path) + except ConfigParseError: + raise + except _MALFORMED_CONFIG_ERRORS as exc: + # Normalise the per-parser "this file is malformed" errors into one + # type: json.JSONDecodeError / tomllib.TOMLDecodeError (ValueError + # subclasses), PyYAML's YAMLError, configparser.Error, and + # xml.etree.ElementTree.ParseError (raised by defusedxml on XML whose + # structure/element name is not well-formed). A bad input file is + # expected when parsing harvested config, so fail closed with a clean + # error instead of an unhandled traceback. + # + # IMPORTANT: this deliberately does NOT catch defusedxml's security + # exceptions (EntitiesForbidden, DTDForbidden, ...). Those signal an + # attempted XXE/entity-expansion attack and must propagate unchanged so + # callers (and tests) can distinguish "malformed" from "malicious". + raise ConfigParseError(f"could not parse {path} as {fmt}: {exc}") from exc # Make sure datetime objects are treated as strings (TOML, YAML) parsed = _stringify_timestamps(parsed) diff --git a/src/jinjaturtle/multi.py b/src/jinjaturtle/multi.py index c968d61..ce54e1c 100644 --- a/src/jinjaturtle/multi.py +++ b/src/jinjaturtle/multi.py @@ -25,13 +25,20 @@ from copy import deepcopy import os import configparser import stat +import sys from dataclasses import dataclass from pathlib import Path from typing import Any, Iterable import xml.etree.ElementTree as ET # nosec from . import j2 -from .core import dump_yaml, flatten_config, make_var_name, parse_config +from .core import ( + dump_yaml, + flatten_config, + make_var_name, + parse_config, + ConfigParseError, +) from .handlers.xml import XmlHandler from .safety import verify_jinja2_template_safe, verify_no_live_jinja_in_json_keys from .escape import escape_jinja_literal @@ -631,7 +638,13 @@ def process_directory( # Parse and group by format grouped: dict[str, list[tuple[Path, Any]]] = defaultdict(list) for p in files: - fmt, parsed = parse_config(p, None) + try: + fmt, parsed = parse_config(p, None) + except ConfigParseError as exc: + # One malformed file should not abort processing of an entire + # directory. Skip it with a warning; the rest still generate. + print(f"jinjaturtle: skipping {p}: {exc}", file=sys.stderr) + continue if fmt not in FOLDER_SUPPORTED_FORMATS: # Directory mode only supports a subset of formats for now. continue diff --git a/tests/test_config_parse_errors.py b/tests/test_config_parse_errors.py new file mode 100644 index 0000000..ab42fe5 --- /dev/null +++ b/tests/test_config_parse_errors.py @@ -0,0 +1,123 @@ +"""Regression tests for malformed-input handling (``ConfigParseError``). + +Bug: every parse-layer handler (xml/json/toml/yaml/ini) used to let its +underlying parser's exception escape as an unhandled traceback when given a +malformed file. Pointing JinjaTurtle (or Enroll, which calls it as a library) +at harvested, attacker-influenceable config makes malformed input an entirely +expected condition, so it must fail cleanly instead of crashing. + +These tests pin down that: + + * ``parse_config`` raises the normalised ``ConfigParseError`` for malformed + XML/JSON/TOML/INI; + * defusedxml's *security* exceptions (XXE / ``EntitiesForbidden``) are NOT + swallowed by that normalisation -- they must still propagate so a caller can + distinguish "malformed" from "malicious"; + * an unrelated error (e.g. the TOML "tomllib missing" ``RuntimeError``) is not + captured by the normalisation either; + * the CLI exits non-zero with a clean message (no traceback) on malformed + input; and + * folder mode skips an unparseable file instead of aborting the whole run. +""" + +from __future__ import annotations + +import subprocess +import sys +from pathlib import Path + +import pytest + +from jinjaturtle.core import ConfigParseError, parse_config + + +def _run_cli(args: list[str]) -> subprocess.CompletedProcess[str]: + return subprocess.run( + [sys.executable, "-m", "jinjaturtle.cli", *args], + capture_output=True, + text=True, + ) + + +@pytest.mark.parametrize( + "fmt,filename,content", + [ + # Element name is not well-formed XML -> expat ParseError historically + # escaped as an uncaught traceback. + ("xml", "bad.xml", "<{{tag}}/>"), + ("xml", "bad2.xml", ""), + ("json", "bad.json", "{not valid json"), + ("toml", "bad.toml", "x = = ="), + # A bare key with no value is invalid INI for configparser. + ("ini", "bad.ini", "[s]\nthis line has no equals and no colon\n"), + ], +) +def test_parse_config_raises_configparseerror_on_malformed( + tmp_path: Path, fmt: str, filename: str, content: str +) -> None: + src = tmp_path / filename + src.write_text(content, encoding="utf-8") + with pytest.raises(ConfigParseError): + parse_config(src, fmt=fmt) + + +def test_parse_config_does_not_swallow_xxe_security_exception(tmp_path: Path) -> None: + """defusedxml's EntitiesForbidden must propagate, not become ConfigParseError. + + EntitiesForbidden subclasses ValueError, so a naive ``except ValueError`` / + ``except Exception`` in parse_config would mask an XXE attempt as a benign + "malformed file". The normalisation is deliberately scoped to exclude it. + """ + from defusedxml.common import EntitiesForbidden + + xxe = ( + '\n' + ' ]>\n' + "&xxe;\n" + ) + src = tmp_path / "xxe.xml" + src.write_text(xxe, encoding="utf-8") + with pytest.raises(EntitiesForbidden): + parse_config(src, fmt="xml") + + +def test_parse_config_does_not_swallow_unrelated_runtimeerror( + tmp_path: Path, monkeypatch +) -> None: + """A non-malformation error (tomllib missing) must propagate unchanged.""" + import jinjaturtle.handlers.toml as toml_module + + monkeypatch.setattr(toml_module, "tomllib", None) + src = tmp_path / "x.toml" + src.write_text('a = "b"\n', encoding="utf-8") + with pytest.raises(RuntimeError) as exc: + parse_config(src, fmt="toml") + assert "tomllib/tomli is required" in str(exc.value) + + +def test_cli_fails_cleanly_on_malformed_xml(tmp_path: Path) -> None: + """The CLI must exit non-zero with a clean message, not a traceback.""" + src = tmp_path / "bad.xml" + src.write_text("<{{tag}}/>", encoding="utf-8") + res = _run_cli([str(src), "-f", "xml", "-r", "demo"]) + assert res.returncode != 0 + # Clean, user-facing message -- not a Python traceback. + assert "could not parse" in res.stderr + assert "Traceback (most recent call last)" not in res.stderr + + +def test_folder_mode_skips_unparseable_file(tmp_path: Path) -> None: + """One malformed file should not abort processing of the whole directory.""" + from jinjaturtle.multi import process_directory + + good = tmp_path / "good.json" + good.write_text('{ "host": "localhost" }', encoding="utf-8") + bad = tmp_path / "bad.json" + bad.write_text("{not valid json", encoding="utf-8") + + defaults_yaml, outputs = process_directory(tmp_path, False, "demo") + # The good file still produced output despite the bad sibling: its content + # and source id appear, and a template was generated. + assert "localhost" in defaults_yaml + assert "good.json" in defaults_yaml + assert outputs From d4fd42522d329d26a25d205e162ab396111a5353 Mon Sep 17 00:00:00 2001 From: Miguel Jacq Date: Mon, 29 Jun 2026 20:53:15 +1000 Subject: [PATCH 19/25] Fix bandit alert --- src/jinjaturtle/core.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/src/jinjaturtle/core.py b/src/jinjaturtle/core.py index de34735..458dbdc 100644 --- a/src/jinjaturtle/core.py +++ b/src/jinjaturtle/core.py @@ -379,7 +379,7 @@ def parse_config(path: Path, fmt: str | None = None) -> tuple[str, Any]: raise except _MALFORMED_CONFIG_ERRORS as exc: # Normalise the per-parser "this file is malformed" errors into one - # type: json.JSONDecodeError / tomllib.TOMLDecodeError (ValueError + # json.JSONDecodeError / tomllib.TOMLDecodeError (ValueError # subclasses), PyYAML's YAMLError, configparser.Error, and # xml.etree.ElementTree.ParseError (raised by defusedxml on XML whose # structure/element name is not well-formed). A bad input file is From 575c2b79f92aeded7490cf94b31cea5341248b53 Mon Sep 17 00:00:00 2001 From: Miguel Jacq Date: Wed, 1 Jul 2026 12:23:19 +1000 Subject: [PATCH 20/25] Fix catching of defusedxml exception --- src/jinjaturtle/cli.py | 15 +++++++++++ tests/test_config_parse_errors.py | 41 +++++++++++++++++++++++++++++++ 2 files changed, 56 insertions(+) diff --git a/src/jinjaturtle/cli.py b/src/jinjaturtle/cli.py index 65dfa72..d901606 100644 --- a/src/jinjaturtle/cli.py +++ b/src/jinjaturtle/cli.py @@ -3,6 +3,7 @@ from __future__ import annotations import argparse import sys from defusedxml import defuse_stdlib +from defusedxml.common import DefusedXmlException from pathlib import Path from . import j2 @@ -77,6 +78,20 @@ def _main(argv: list[str] | None = None) -> int: except OutputPathError as exc: print(f"jinjaturtle: refusing unsafe output path: {exc}", file=sys.stderr) return 2 + except DefusedXmlException as exc: + # defusedxml rejected the XML because it attempted a DTD, entity + # expansion, or external reference (XXE / billion-laughs class attack). + # This is a deliberately-blocked attack, not a benign malformed file, so + # core.parse_config lets it propagate unchanged rather than folding it + # into ConfigParseError. Report it as a refused unsafe input with a + # non-zero exit code instead of leaking an internal traceback. + print( + "jinjaturtle: refusing unsafe XML input: the document uses a DTD, " + f"entity expansion, or external reference ({exc.__class__.__name__}). " + "This is blocked to prevent XXE / entity-expansion attacks.", + file=sys.stderr, + ) + return 2 except ConfigParseError as exc: # The source file could not be parsed as its (detected or forced) # format. This is expected for malformed/attacker-influenced input; diff --git a/tests/test_config_parse_errors.py b/tests/test_config_parse_errors.py index ab42fe5..01ba1ef 100644 --- a/tests/test_config_parse_errors.py +++ b/tests/test_config_parse_errors.py @@ -106,6 +106,47 @@ def test_cli_fails_cleanly_on_malformed_xml(tmp_path: Path) -> None: assert "Traceback (most recent call last)" not in res.stderr +@pytest.mark.parametrize( + "content", + [ + # Classic XXE: external SYSTEM entity used to read a local file. + ( + '\n' + ']>\n' + "&xxe;\n" + ), + # Billion-laughs style internal entity expansion. + ( + '\n' + ']>\n' + "&lol2;\n" + ), + # External parameter entity (SSRF / out-of-band XXE vector). + ( + '\n' + ' %ext;]>\n' + "x\n" + ), + ], +) +def test_cli_refuses_xxe_cleanly(tmp_path: Path, content: str) -> None: + """defusedxml's security refusal must surface as a clean non-zero exit. + + ``EntitiesForbidden``/``DTDForbidden``/``ExternalReferenceForbidden`` subclass + ``DefusedXmlException`` (and ``ValueError``). ``parse_config`` deliberately + lets them propagate rather than folding them into ``ConfigParseError`` so a + blocked attack stays distinguishable from a benign malformed file. The CLI + must therefore catch ``DefusedXmlException`` itself and exit cleanly instead + of leaking a Python traceback. + """ + src = tmp_path / "xxe.xml" + src.write_text(content, encoding="utf-8") + res = _run_cli([str(src), "-f", "xml", "-r", "demo"]) + assert res.returncode == 2 + assert "refusing unsafe XML input" in res.stderr + assert "Traceback (most recent call last)" not in res.stderr + + def test_folder_mode_skips_unparseable_file(tmp_path: Path) -> None: """One malformed file should not abort processing of the whole directory.""" from jinjaturtle.multi import process_directory From 054b90ebde1709d6f9dc1823e3c6d23770a24b55 Mon Sep 17 00:00:00 2001 From: Miguel Jacq Date: Thu, 2 Jul 2026 14:22:07 +1000 Subject: [PATCH 21/25] Don't reference built-in globals via loop-items in Jinja2 into keys --- src/jinjaturtle/handlers/json.py | 10 ++++++++- src/jinjaturtle/handlers/toml.py | 14 +++++++++++- src/jinjaturtle/handlers/yaml.py | 13 +++++++++++ src/jinjaturtle/loop_analyzer.py | 37 +++++++++++++++++++++++++++++++ src/jinjaturtle/safety.py | 38 ++++++++++++++++++++++++++++++++ 5 files changed, 110 insertions(+), 2 deletions(-) diff --git a/src/jinjaturtle/handlers/json.py b/src/jinjaturtle/handlers/json.py index 0268666..41699c9 100644 --- a/src/jinjaturtle/handlers/json.py +++ b/src/jinjaturtle/handlers/json.py @@ -8,7 +8,7 @@ from typing import Any from . import DictLikeHandler from .. import j2 from ..escape import escape_jinja_literal -from ..loop_analyzer import LoopCandidate +from ..loop_analyzer import LoopCandidate, is_safe_loop_field_key class JsonHandler(DictLikeHandler): @@ -383,6 +383,14 @@ class JsonHandler(DictLikeHandler): ] # first line has no indent; we prepend `inner` when emitting for i, key in enumerate(keys): comma = "," if i < len(keys) - 1 else "" + # Defence in depth: never interpolate a raw source key into an + # ``item_var.key`` reference. A key such as ``a }}{{ x`` would break + # out of the value placeholder and inject a live construct that the + # output-safety gate cannot distinguish from a legitimate variable. + if not is_safe_loop_field_key(key): + raise ValueError( + f"refusing to emit loop-item field reference for unsafe key: {key!r}" + ) # The literal key text is emitted verbatim into the template; escape any # Jinja markup in it. The value side ({item_var}.{key}) is constrained by # the output safety gate's dotted-name allowlist, which fails closed on diff --git a/src/jinjaturtle/handlers/toml.py b/src/jinjaturtle/handlers/toml.py index 6d25cff..b2aa6e5 100644 --- a/src/jinjaturtle/handlers/toml.py +++ b/src/jinjaturtle/handlers/toml.py @@ -6,7 +6,7 @@ from typing import Any from . import DictLikeHandler from .. import j2 from ..escape import escape_jinja_literal -from ..loop_analyzer import LoopCandidate +from ..loop_analyzer import LoopCandidate, is_safe_loop_field_key try: import tomllib @@ -438,6 +438,18 @@ class TomlHandler(DictLikeHandler): for key, value in sample_item.items(): if key == "_key": continue + # Defence in depth: the loop analyzer refuses a + # dict-loop whose items contain a non-identifier + # key, so ``key`` is always a plain identifier + # here. Never interpolate a raw key into an + # ``item_var.key`` reference: a key such as + # ``a }}{{ x`` would break out of the placeholder + # and inject a live construct. + if not is_safe_loop_field_key(key): + raise ValueError( + "refusing to emit loop-item field " + f"reference for unsafe key: {key!r}" + ) if isinstance(value, str): out_lines.append( f"{escape_jinja_literal(str(key))} = " diff --git a/src/jinjaturtle/handlers/yaml.py b/src/jinjaturtle/handlers/yaml.py index d8131b0..a1447bb 100644 --- a/src/jinjaturtle/handlers/yaml.py +++ b/src/jinjaturtle/handlers/yaml.py @@ -7,6 +7,7 @@ from typing import Any from .dict import DictLikeHandler from .. import j2 from ..escape import escape_jinja_literal +from ..loop_analyzer import is_safe_loop_field_key from ..loop_analyzer import LoopCandidate @@ -547,6 +548,18 @@ class YamlHandler(DictLikeHandler): # Special key for dict collections - output as comment or skip continue + # Defence in depth: the loop analyzer already refuses a dict-loop + # whose items contain a non-identifier key (see _analyze_dict_schema), + # so ``key`` should always be a plain identifier here. Assert it + # rather than interpolate a raw key into a Jinja reference: a key such + # as ``a }}{{ x`` would otherwise close the placeholder and inject a + # live construct that the output gate cannot distinguish from a + # legitimate variable. + if not is_safe_loop_field_key(key): + raise ValueError( + f"refusing to emit loop-item field reference for unsafe key: {key!r}" + ) + if first_key and is_list_item: # First key gets the list marker value_expr = self._yaml_value_expr(f"{loop_var}.{key}", value) diff --git a/src/jinjaturtle/loop_analyzer.py b/src/jinjaturtle/loop_analyzer.py index 23702d8..608c8e4 100644 --- a/src/jinjaturtle/loop_analyzer.py +++ b/src/jinjaturtle/loop_analyzer.py @@ -7,10 +7,34 @@ instead of flattened scalar variables. from __future__ import annotations +import re from collections import Counter from typing import Any, Literal +# A dict-loop emits per-item field references of the form ``loopvar.``. +# ```` is derived from a source key, which is attacker-influenceable when +# JinjaTurtle is fed harvested config. The output-safety gate only accepts a +# reference whose every hop matches this identifier class, so a key must reduce +# to exactly this shape before it can be used as a loop-item field. Anything else +# (a key containing ``}}``, quotes, ``.``, ``__``, ...) must not be turned into a +# loop; the caller falls back to scalar generation, where every value goes through +# make_var_name() and all verbatim text is escaped. +_SAFE_LOOP_FIELD_RE = re.compile(r"(?!\w*__)[A-Za-z_][A-Za-z0-9_]*\Z") + + +def is_safe_loop_field_key(key: Any) -> bool: + """Return True if *key* is safe to emit as a ``loopvar.`` field access. + + The check mirrors the output-safety gate's identifier class (single + identifier, no double underscore). A key that does not match cannot be + expressed as a dotted loop-item reference without risking template + injection, so a loop candidate containing such a key is rejected upstream. + """ + + return bool(_SAFE_LOOP_FIELD_RE.match(str(key))) + + class LoopCandidate: """ Represents a detected loop opportunity in the config structure. @@ -265,6 +289,19 @@ class LoopAnalyzer: if not dicts: return "heterogeneous" + # Security: a dict-loop emits ``loopvar.`` field references. If any + # item key is not a plain identifier, it cannot be expressed safely as a + # dotted reference (a key such as ``a }}{{ x`` would break out of the + # placeholder and inject a live construct). Refuse the loop so the caller + # falls back to scalar generation, which escapes all verbatim text and + # routes every value through make_var_name(). + for d in dicts: + for k in d.keys(): + if k == "_key": + continue + if not is_safe_loop_field_key(k): + return "heterogeneous" + # Get key sets from each dict key_sets = [set(d.keys()) for d in dicts] diff --git a/src/jinjaturtle/safety.py b/src/jinjaturtle/safety.py index 5ed2fe1..e049dd3 100644 --- a/src/jinjaturtle/safety.py +++ b/src/jinjaturtle/safety.py @@ -132,13 +132,51 @@ def _strip_ws_control(body: str) -> str: return body.strip() +# Built-in Jinja2/Ansible globals that JinjaTurtle never emits as a reference +# head. The allowlist grammar necessarily accepts any bare identifier (it cannot +# tell an injected global from a legitimate generated variable), so these names +# are rejected explicitly: their presence as the head of a live reference means +# source text leaked into a live construct. This is a targeted backstop and does +# not replace the grammar check. +_FORBIDDEN_REFERENCE_HEADS = frozenset( + { + "range", + "dict", + "lipsum", + "cycler", + "joiner", + "namespace", + "config", + "self", + "cycle", + "request", + "get_flashed_messages", + "url_for", + } +) + + +def _reference_head(body: str) -> str: + """Return the leading identifier (before any dot/filter) of an expression.""" + body = _strip_ws_control(body) + m = re.match(r"[A-Za-z_][A-Za-z0-9_]*", body) + return m.group(0) if m else "" + + def _expr_is_allowed(body: str) -> bool: body = _strip_ws_control(body) + if _reference_head(body) in _FORBIDDEN_REFERENCE_HEADS: + return False return any(p.match(body) for p in _EXPR_PATTERNS) def _stmt_is_allowed(body: str) -> bool: body = _strip_ws_control(body) + # A ``for ... in `` whose collection is a forbidden global is + # rejected for the same reason as an expression head. + m = re.match(r"for\s+[A-Za-z_]\w*\s+in\s+([A-Za-z_][A-Za-z0-9_]*)", body) + if m and m.group(1) in _FORBIDDEN_REFERENCE_HEADS: + return False return any(p.match(body) for p in _STMT_PATTERNS) From c6ce0311edcaba99ba4a471e87e8c9751a762112 Mon Sep 17 00:00:00 2001 From: Miguel Jacq Date: Thu, 2 Jul 2026 14:52:09 +1000 Subject: [PATCH 22/25] Forbid the ansible globals --- src/jinjaturtle/safety.py | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/src/jinjaturtle/safety.py b/src/jinjaturtle/safety.py index e049dd3..938f2ad 100644 --- a/src/jinjaturtle/safety.py +++ b/src/jinjaturtle/safety.py @@ -152,6 +152,13 @@ _FORBIDDEN_REFERENCE_HEADS = frozenset( "request", "get_flashed_messages", "url_for", + # Ansible global set + "lookup", + "q", + "query", + "now", + "omit", + "undef", } ) From f9332879ba4a9b550861dc4bc6df4e0d20d8fcf9 Mon Sep 17 00:00:00 2001 From: Miguel Jacq Date: Fri, 3 Jul 2026 12:23:52 +1000 Subject: [PATCH 23/25] More hardening --- src/jinjaturtle/core.py | 16 ++++++++++-- src/jinjaturtle/handlers/yaml.py | 41 ++++++++++++++++++++++++++++++- tests/test_config_parse_errors.py | 41 +++++++++++++++++++++++++++++++ 3 files changed, 95 insertions(+), 3 deletions(-) diff --git a/src/jinjaturtle/core.py b/src/jinjaturtle/core.py index 458dbdc..de7b552 100644 --- a/src/jinjaturtle/core.py +++ b/src/jinjaturtle/core.py @@ -375,6 +375,10 @@ def parse_config(path: Path, fmt: str | None = None) -> tuple[str, Any]: raise ValueError(f"Unsupported config format: {fmt}") try: parsed = handler.parse(path) + # Make sure datetime objects are treated as strings (TOML, YAML). This + # walks the parsed object recursively, so keep it inside the try where a + # RecursionError from a pathological structure is normalised below. + parsed = _stringify_timestamps(parsed) except ConfigParseError: raise except _MALFORMED_CONFIG_ERRORS as exc: @@ -391,8 +395,16 @@ def parse_config(path: Path, fmt: str | None = None) -> tuple[str, Any]: # attempted XXE/entity-expansion attack and must propagate unchanged so # callers (and tests) can distinguish "malformed" from "malicious". raise ConfigParseError(f"could not parse {path} as {fmt}: {exc}") from exc - # Make sure datetime objects are treated as strings (TOML, YAML) - parsed = _stringify_timestamps(parsed) + except RecursionError as exc: + # A deeply-nested or self-referential structure (e.g. a recursive YAML + # anchor) can exhaust the Python stack while walking the parsed object. + # The YAML handler already rejects reference cycles up front; this is a + # format-agnostic backstop so any such input fails closed with a clean + # message instead of a stack-overflow traceback. + raise ConfigParseError( + f"could not parse {path} as {fmt}: input is too deeply nested " + "or self-referential" + ) from exc return fmt, parsed diff --git a/src/jinjaturtle/handlers/yaml.py b/src/jinjaturtle/handlers/yaml.py index a1447bb..9a868a6 100644 --- a/src/jinjaturtle/handlers/yaml.py +++ b/src/jinjaturtle/handlers/yaml.py @@ -11,6 +11,36 @@ from ..loop_analyzer import is_safe_loop_field_key from ..loop_analyzer import LoopCandidate +def _reject_recursive_structure(obj: Any) -> None: + """Raise ``yaml.YAMLError`` if *obj* contains a reference cycle. + + A recursive YAML anchor (``a: &a [*a]``) produces a container that contains + itself. Every consumer in JinjaTurtle walks the parsed object depth-first, + so a cycle would raise ``RecursionError`` deep in unrelated code. Detect it + up front by tracking the ``id()`` of containers on the current descent path; + a repeat means a cycle. ``yaml.YAMLError`` is raised so ``parse_config`` + normalises it into a clean ``ConfigParseError`` like any other malformed + input, rather than surfacing a stack-overflow traceback. + """ + + on_path: set[int] = set() + + def walk(node: Any) -> None: + if isinstance(node, (dict, list)): + marker = id(node) + if marker in on_path: + raise yaml.YAMLError( + "recursive/self-referential YAML structure is not supported" + ) + on_path.add(marker) + children = node.values() if isinstance(node, dict) else node + for child in children: + walk(child) + on_path.discard(marker) + + walk(obj) + + class YamlHandler(DictLikeHandler): """ YAML handler that can generate both scalar templates and loop-based templates. @@ -21,7 +51,16 @@ class YamlHandler(DictLikeHandler): def parse(self, path: Path) -> Any: text = path.read_text(encoding="utf-8") - return yaml.safe_load(text) or {} + parsed = yaml.safe_load(text) or {} + # PyYAML's safe_load happily builds *recursive* structures from an anchor + # that references itself (e.g. ``a: &a [*a]``). Downstream flattening, + # timestamp-stringifying and template generation all walk the parsed + # object recursively and would blow the Python stack (RecursionError) on + # such input. JinjaTurtle is regularly pointed at harvested, + # attacker-influenceable config, so reject a self-referential document + # cleanly here rather than crashing later. + _reject_recursive_structure(parsed) + return parsed def generate_jinja2_template( self, diff --git a/tests/test_config_parse_errors.py b/tests/test_config_parse_errors.py index 01ba1ef..7f4c422 100644 --- a/tests/test_config_parse_errors.py +++ b/tests/test_config_parse_errors.py @@ -162,3 +162,44 @@ def test_folder_mode_skips_unparseable_file(tmp_path: Path) -> None: assert "localhost" in defaults_yaml assert "good.json" in defaults_yaml assert outputs + + +@pytest.mark.parametrize( + "content", + [ + "a: &a [*a]\n", # self-referential sequence alias + "root: &r\n child: *r\n", # self-referential mapping alias + ], +) +def test_recursive_yaml_is_rejected_cleanly(tmp_path: Path, content: str) -> None: + """A recursive YAML anchor must fail as a clean ConfigParseError. + + PyYAML's safe_load builds a self-referential object from a recursive anchor; + JinjaTurtle's downstream walks (flatten, timestamp-stringify, template gen) + would otherwise blow the stack with a RecursionError traceback. Harvested + config is attacker-influenceable, so this must fail closed. + """ + src = tmp_path / "cyclic.yaml" + src.write_text(content, encoding="utf-8") + with pytest.raises(ConfigParseError): + parse_config(src, "yaml") + + +def test_recursive_yaml_cli_exits_nonzero_without_traceback(tmp_path: Path) -> None: + src = tmp_path / "cyclic.yaml" + src.write_text("a: &a [*a]\n", encoding="utf-8") + res = _run_cli([str(src), "-f", "yaml", "-r", "role"]) + assert res.returncode != 0 + assert "Traceback" not in res.stderr + assert "RecursionError" not in res.stderr + + +def test_shared_noncyclic_yaml_aliases_still_work(tmp_path: Path) -> None: + """A shared (acyclic) anchor referenced multiple times is a DAG, not a + cycle, and must still parse and template normally.""" + src = tmp_path / "shared.yaml" + src.write_text("base: &b\n x: 1\na: *b\nc: *b\n", encoding="utf-8") + fmt, parsed = parse_config(src, "yaml") + assert fmt == "yaml" + assert parsed["a"] == {"x": 1} + assert parsed["c"] == {"x": 1} From d3694240dab9a9ed64e4be8a74c408a1c17a0ba4 Mon Sep 17 00:00:00 2001 From: Miguel Jacq Date: Sun, 5 Jul 2026 10:54:37 +1000 Subject: [PATCH 24/25] 0.7.0 --- debian/changelog | 6 ++++++ pyproject.toml | 2 +- rpm/jinjaturtle.spec | 4 +++- 3 files changed, 10 insertions(+), 2 deletions(-) diff --git a/debian/changelog b/debian/changelog index 9173c94..be6b123 100644 --- a/debian/changelog +++ b/debian/changelog @@ -1,3 +1,9 @@ +jinjaturtle (0.7.0) unstable; urgency=medium + + * Much hardening. + + -- Miguel Jacq Sun, 5 Jul 2026 10:54:00 +1000 + jinjaturtle (0.5.7) unstable; urgency=medium * More hardening measures diff --git a/pyproject.toml b/pyproject.toml index 9ec2da5..7751303 100644 --- a/pyproject.toml +++ b/pyproject.toml @@ -1,6 +1,6 @@ [project] name = "jinjaturtle" -version = "0.5.7" +version = "0.7.0" description = "Convert config files into Ansible defaults and Jinja2 templates." authors = [ { name = "Miguel Jacq", email = "mig@mig5.net" }, diff --git a/rpm/jinjaturtle.spec b/rpm/jinjaturtle.spec index 051fd8b..8c8d845 100644 --- a/rpm/jinjaturtle.spec +++ b/rpm/jinjaturtle.spec @@ -1,4 +1,4 @@ -%global upstream_version 0.5.7 +%global upstream_version 0.7.0 Name: jinjaturtle Version: %{upstream_version} @@ -42,6 +42,8 @@ Convert config files into Ansible defaults and Jinja2 templates. %{_bindir}/jinjaturtle %changelog +* Sun Jul 05 2026 Miguel Jacq - %{version}-%{release} +- Much hardening * Wed Jun 24 2026 Miguel Jacq - %{version}-%{release} - More hardening * Tue Jun 23 2026 Miguel Jacq - %{version}-%{release} From a712b19a45c0be6403a00daf1434cc48e3cc7f95 Mon Sep 17 00:00:00 2001 From: Miguel Jacq Date: Fri, 24 Jul 2026 10:58:23 +1000 Subject: [PATCH 25/25] Remove Fediverse link --- README.md | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) diff --git a/README.md b/README.md index 1726719..5e104f3 100644 --- a/README.md +++ b/README.md @@ -275,7 +275,4 @@ management system! ## Found a bug, have a suggestion? -You can e-mail me; see `pyproject.toml` for details. You can also contact me on -the Fediverse: - -https://goto.mig5.net/@mig5 +You can e-mail me; see `pyproject.toml` for details.