texmark 0.0.0__tar.gz

texmark-0.0.0/.gitattributes

@@ -0,0 +1,4 @@
+*.pdf filter=lfs diff=lfs merge=lfs -text
+*.png filter=lfs diff=lfs merge=lfs -text
+*.eps filter=lfs diff=lfs merge=lfs -text
+*.ps filter=lfs diff=lfs merge=lfs -text

texmark-0.0.0/.github/workflows/pypi.yml

@@ -0,0 +1,35 @@
+name: Publish to PyPI
+
+on:
+  push:
+    tags:
+      - '*'
+
+jobs:
+  build-and-publish:
+    runs-on: ubuntu-latest
+    environment:
+      name: pypi
+    permissions:
+      id-token: write  # This is required for OIDC
+      contents: read
+
+    steps:
+    - name: Checkout code
+      uses: actions/checkout@v2
+
+    - name: Set up Python
+      uses: actions/setup-python@v2
+      with:
+        python-version: '3.x'
+
+    - name: Install dependencies
+      run: |
+        python -m pip install --upgrade pip
+        pip install setuptools setuptools-scm[toml] wheel build
+
+    - name: Build distribution
+      run: python -m build
+
+    - name: Publish to PyPI
+      uses: pypa/gh-action-pypi-publish@release/v1

texmark-0.0.0/.gitignore

@@ -0,0 +1,174 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# UV
+#   Similar to Pipfile.lock, it is generally recommended to include uv.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#uv.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/latest/usage/project/#working-with-version-control
+.pdm.toml
+.pdm-python
+.pdm-build/
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/
+
+# Ruff stuff:
+.ruff_cache/
+
+# PyPI configuration file
+.pypirc

texmark-0.0.0/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2025 Mahé Perrette
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

texmark-0.0.0/PKG-INFO

@@ -0,0 +1,68 @@
+Metadata-Version: 2.4
+Name: texmark
+Version: 0.0.0
+Summary: Write scientific articles in markdown
+Author-email: Mahé Perrette <mahe.perrette@gmail.com>
+Project-URL: homepage, https://github.com/perrette/texmark
+Requires-Python: >=3.9
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: pypandoc
+Requires-Dist: jinja2
+Requires-Dist: pyyaml
+Requires-Dist: panflute
+Requires-Dist: python-frontmatter
+Dynamic: license-file
+
+# texmark
+
+Write scientific articles in markdown
+
+
+## Installation
+
+for development, after cloning:
+
+    pip install -e .
+
+and soon:
+
+    pip install texmark
+
+## Example
+
+See [example.md](example.md) for a sample markdown file with yaml metadata in the header.
+
+The command to convert the markdow to tex is:
+
+    texmark example.md
+
+And to convert to PDF
+
+    texmark example.md --pdf
+
+For another journal, it is enough to change the `journal -> template' field in the yaml metadata.
+For testing it is also possible to pass `-j` for `--journal-template`:
+
+    texmark example.md --pdf -j science -o build/example-science.pdf --tex build/example-science.tex
+
+See the example tex and pdf results in [build](/build)
+
+For now only `copernicus` and `science` template are available.
+Only partial support is provided. Upon submission you'll most likely need
+to rework the final latex version, especially to handle things like appendix or special sections.
+Alternatively, you may write your custom template (see the advanced section)
+
+## Advanced: latex template
+
+The templates are written in [jinja2](https://jinja.palletsprojects.com).
+
+Just copy from e.g. texmark/templates/science/template.tex to your own, e.g. custom_template.tex
+And run again with:
+
+    texmark example.md --pdf -j science -o build/example-science.pdf --tex build/example-science.tex --template custom_template.tex
+
+The -j journal template option (here `science`) is still used to set custom filters (e.g. only `\cite` for Science, no `\citet` ; extract specific sections as metadata to be injected as `{{section}}` instead of `{{body}}` etc). The machinery is defined in [texmark/filters.py](/texmark/filters.py) and can in principle be extended or copied.
+Two approaches are possible:
+- just add more filters via the `--filters` command or in the yaml metadata.
+- extend the existing filters in a module, e.g. custom_filter.py, that extends the `filters` dict from the `texmark.filters` module (see the source code to check the details). And then pass it via `--filters-module custom_filter` parameter (or `custom_filter` in the metadata) to prompt the texmark filter to load that module and make it available via `-j your-custom-name`. Note that will require you to explicitly pass `--template` as well. Unless you overwrite an existing filter.

texmark-0.0.0/README.md

@@ -0,0 +1,52 @@
+# texmark
+
+Write scientific articles in markdown
+
+
+## Installation
+
+for development, after cloning:
+
+    pip install -e .
+
+and soon:
+
+    pip install texmark
+
+## Example
+
+See [example.md](example.md) for a sample markdown file with yaml metadata in the header.
+
+The command to convert the markdow to tex is:
+
+    texmark example.md
+
+And to convert to PDF
+
+    texmark example.md --pdf
+
+For another journal, it is enough to change the `journal -> template' field in the yaml metadata.
+For testing it is also possible to pass `-j` for `--journal-template`:
+
+    texmark example.md --pdf -j science -o build/example-science.pdf --tex build/example-science.tex
+
+See the example tex and pdf results in [build](/build)
+
+For now only `copernicus` and `science` template are available.
+Only partial support is provided. Upon submission you'll most likely need
+to rework the final latex version, especially to handle things like appendix or special sections.
+Alternatively, you may write your custom template (see the advanced section)
+
+## Advanced: latex template
+
+The templates are written in [jinja2](https://jinja.palletsprojects.com).
+
+Just copy from e.g. texmark/templates/science/template.tex to your own, e.g. custom_template.tex
+And run again with:
+
+    texmark example.md --pdf -j science -o build/example-science.pdf --tex build/example-science.tex --template custom_template.tex
+
+The -j journal template option (here `science`) is still used to set custom filters (e.g. only `\cite` for Science, no `\citet` ; extract specific sections as metadata to be injected as `{{section}}` instead of `{{body}}` etc). The machinery is defined in [texmark/filters.py](/texmark/filters.py) and can in principle be extended or copied.
+Two approaches are possible:
+- just add more filters via the `--filters` command or in the yaml metadata.
+- extend the existing filters in a module, e.g. custom_filter.py, that extends the `filters` dict from the `texmark.filters` module (see the source code to check the details). And then pass it via `--filters-module custom_filter` parameter (or `custom_filter` in the metadata) to prompt the texmark filter to load that module and make it available via `-j your-custom-name`. Note that will require you to explicitly pass `--template` as well. Unless you overwrite an existing filter.

texmark-0.0.0/example.md

@@ -0,0 +1,59 @@
+---
+title: "This is an example title"
+authors:
+  - firstname: Mahé
+    lastname: Perrette
+    affiliation: 1
+    email: mahe.perrette@gmail.com
+  - firstname: Another
+    lastname: Author
+    affiliation: 2
+affiliations:
+  - "Alfred Wegener Institut fur Meeres und Polarforschung (AWI)"
+  - "Another Institution in a Remote Country"
+running:
+    title: LGM data assimilation
+    author: Perrette et al
+date: "2025-07-15"
+bibliography: references.bib
+journal:
+    short: cp
+    template: copernicus
+---
+
+# Abstract
+
+The abstract will be identified and moved to the metadata,
+so that it can be used as in the journal templates.
+
+Each journal has its own template. For now only Copernicus and Science are covered.
+
+# Introduction
+
+The journal templates can be edited in [texmark/templates](/texmark/templates)
+and journal-specific filters can be added such as for [copernicus](/texmark/copernicus.py).
+
+Lots of research has been done on that topic.
+We focus mostly on @tierney_zhu2020
+but also on \cite{tierney_zhu2020}
+
+![My figure \label{fig:eofmean}. The leading / in images and links is removed, but it is convenient for proper formatting in github.](/images/eof_mean.png)
+
+That's an inline equation $a + 1 = 3$.
+And a block equation
+$$
+a + \Sigma_i i^2
+$$
+and an align environment
+\begin{align} \label{eq:aligneq}
+a &= 9 + 2 \\
+b &= 3
+\end{align}
+
+Now i can cite Eq. \ref{eq:aligneq} and my figure \ref{fig:eofmean}
+
+Both latex and markdown commands are supported.
+
+# Conclusions
+
+This is also a special section.

texmark-0.0.0/images/eof_mean.png

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a80a00876ad992bd64774a3d2996695e4d09298a074134666f9d0bff2b90addd
+size 80641

texmark-0.0.0/pyproject.toml

@@ -0,0 +1,34 @@
+[build-system]
+requires = ["setuptools>=61.0", "setuptools_scm[toml]>=6.2"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "texmark"
+authors = [
+    {name = "Mahé Perrette", email = "mahe.perrette@gmail.com"},
+]
+description='Write scientific articles in markdown'
+readme = "README.md"
+requires-python = ">=3.9"
+# license = {text = "MIT"}
+
+dynamic = ["version", "dependencies"]
+
+[tool.setuptools.dynamic]
+dependencies =  {file = ["requirements.txt"]}
+
+[project.urls]
+homepage = "https://github.com/perrette/texmark"
+
+[tool.setuptools.packages.find]
+where = ["."]
+include = [
+    "texmark",
+]
+
+[ tool.setuptools.package-data ]
+texmark = ["templates/**/*"]
+
+[project.scripts]
+texmark = "texmark.build:main"
+texmark-filter = "texmark.filters:main"

texmark-0.0.0/references.bib

@@ -0,0 +1,13 @@
+
+@article{tierney_zhu2020,
+ author = {Tierney, Jessica E. and Zhu, Jiang and King, Jonathan and Malevich, Steven B. and Hakim, Gregory J. and Poulsen, Christopher J.},
+ doi = {10.1038/s41586-020-2617-x},
+ file = {:../../Documents/papers/lgmdataassim/tierney_et_al_2020_glacial-cooling-and-climate-sensitivity-revisited.pdf:pdf},
+ journal = {Nature},
+ number = {7822},
+ pages = {569-573},
+ title = {Glacial cooling and climate sensitivity revisited},
+ url = {https://doi.org/10.1038/s41586-020-2617-x},
+ volume = {584},
+ year = {2020}
+}

texmark-0.0.0/requirements.txt

@@ -0,0 +1,5 @@
+pypandoc
+jinja2
+pyyaml
+panflute
+python-frontmatter

texmark-0.0.0/setup.cfg

@@ -0,0 +1,4 @@
+[egg_info]
+tag_build = 
+tag_date = 0
+

texmark-0.0.0/texmark/build.py

@@ -0,0 +1,178 @@
+#!/usr/bin/env python3
+import subprocess
+from pathlib import Path
+import os
+import sys
+import pypandoc
+import json
+import yaml
+import jinja2
+import frontmatter
+import argparse
+import texmark
+import json
+import panflute as pf
+import io
+from texmark.logs import logger
+
+rootpath = Path(texmark.__file__).resolve().parent
+
+def run(cmd, shell=False, check=True, **kwargs):
+    print(cmd if shell else ' '.join(cmd))
+    return subprocess.run(cmd, shell=shell, check=check, **kwargs)
+
+
+def normalize_metadata(meta):
+    """
+    Recursively convert panflute metadata into plain JSON-serializable Python dict.
+    (Plain strings, lists, dicts, no MetaInlines etc.)
+    """
+    if isinstance(meta, pf.MetaInlines) or isinstance(meta, pf.MetaBlocks):
+        return pf.stringify(meta)
+    elif isinstance(meta, pf.MetaString):
+        return meta.text
+    elif isinstance(meta, pf.MetaBool):
+        return bool(meta)
+    elif isinstance(meta, pf.MetaList):
+        return [normalize_metadata(item) for item in meta]
+    elif isinstance(meta, pf.MetaMap):
+        return {key: normalize_metadata(value) for key, value in meta.items()}
+    else:
+        # Primitive types (str, int, etc.) or unknown - return as is
+        return meta
+
+
+def build_tex(input_md, output_tex, template='', bib_file='', build_dir='build', filters=None, journal_template=None, filters_module=None):
+    # 1. Parse Markdown
+    input_text = open(input_md).read()
+    post = frontmatter.loads(input_text)
+    metadata = post.metadata
+    content = post.content
+
+    if not journal_template:
+        journal_template = metadata.get('journal', {}).get('template', 'default')
+        if not journal_template:
+            journal_template = "default"
+
+    metadata.setdefault('journal', {})['template'] = journal_template
+
+    if filters_module:
+        metadata['filters_module'] = filters_module
+
+    if not template:
+        template = metadata.get('template')
+        if not template:
+            template = f'templates/{journal_template}/template.tex'
+
+    template_folder = Path(template).parent
+    template_name = Path(template).name
+    resource_path = rootpath / template_folder
+
+    if not bib_file:
+        bib_file = metadata.get('bibliography', None)
+    if bib_file:
+        bib_args = ['--bibliography', bib_file]
+    args = bib_args + metadata.get('pandoc_args', []) + [
+        "--natbib",
+    ]
+
+    filters = [
+        "texmark-filter",
+        ] + (filters or metadata.get('filters', []))
+
+    # Step 1: Run pandoc to get JSON AST with filters applied, and updated metadata
+    cmd_json = []
+    for f in filters:
+        cmd_json.extend(['--filter', f])
+    cmd_json.extend(args)
+
+    post.metadata = metadata
+
+    ast_json_str = pypandoc.convert_text(
+        frontmatter.dumps(post),
+        format="markdown+footnotes",
+        to="json",
+        extra_args=cmd_json,
+    )
+
+    doc = pf.load(io.StringIO(ast_json_str))  # <-- no input_format argument
+    metadata.update(normalize_metadata(doc.metadata))
+
+    # Step 2. Render Jinja2 Template
+    env = jinja2.Environment(loader=jinja2.FileSystemLoader(resource_path))
+    template = env.get_template(template_name)
+
+    build_dir = Path(build_dir)
+    build_dir.mkdir(parents=True, exist_ok=True)
+
+    Path(output_tex).parent.mkdir(parents=True, exist_ok=True)
+
+    # Step 3: Render AST to LaTeX (filters not needed again)
+    body = pypandoc.convert_text(
+        ast_json_str,
+        format="json",
+        to="latex",
+        extra_args=['--template', rootpath / "templates" / "body.tex"] + args,
+    )
+
+    with open(output_tex, "w") as f:
+        f.write(template.render(body=body, **metadata))  # Includes authors/abstract
+
+    metadata["resource_path"] = str(resource_path)
+    return metadata
+
+
+def compile_pdf(input_tex, output_pdf, engine='pdflatex', build_dir='build', images_dir='images', bib_file='references.bib', resource_path=''):
+    """
+    Step 2: Compile LaTeX source into PDF.
+    """
+    if resource_path:
+        print(f"Resource path: {resource_path}")
+        run(f"rsync -r {resource_path}/ {build_dir}/", shell=True)
+        # os.environ['TEXINPUTS'] = f"{resource_path}:" + os.environ.get('TEXINPUTS', '')
+
+    run(f"rsync -r {Path(images_dir)} {build_dir}/", shell=True)
+    run(f"rsync {input_tex} {build_dir}/", shell=True)
+    run(f"rsync {bib_file} {build_dir}/", shell=True)
+    cmd = [engine, '-interaction=nonstopmode', Path(input_tex).name]
+    run(cmd, cwd=build_dir, check=False)
+    bibcmd = ["bibtex", Path(input_tex).with_suffix(".aux").name]
+    run(bibcmd, cwd=build_dir, check=False)
+    run(cmd, cwd=build_dir, check=False)
+    run(cmd, cwd=build_dir, check=False)
+    # Rename/move the generated PDF if needed
+    actual_pdf = Path(build_dir) / Path(input_tex).with_suffix(".pdf").name
+    if Path(output_pdf) != actual_pdf:
+        run(['mv', str(actual_pdf), output_pdf])
+
+
+def main():
+
+    parser = argparse.ArgumentParser(description='Two-step build: Markdown → LaTeX → PDF')
+    parser.add_argument('input', help='Input markdown file')
+    parser.add_argument('-j', '--journal-template', help='Pandoc LaTeX + filter template family. Update journal -> template yaml field)')
+    parser.add_argument('-t', '--template', help='Pandoc LaTeX template. Update template yaml field)')
+    parser.add_argument('-f', '--filters', nargs='*', help='Additional, custom filters. By default the pre-defined, custom filters for the journal are used via the `texmark-filter` utility.')
+    parser.add_argument('--filters-module', help='Load a custom filter module. This is a Python module that may extend the filters dict defined in the `texmark.shared` module.')
+    parser.add_argument('-o', '--output', help='Final PDF output filename')
+    parser.add_argument('-e', '--engine', default='pdflatex', help='LaTeX engine (e.g. pdflatex, xelatex)')
+    parser.add_argument('-d', '--build', default='build', help='build directory')
+    parser.add_argument('--bib', help='bibliography file')
+    parser.add_argument('--tex', help='LaTeX output filename')
+    parser.add_argument('--pdf', action="store_true")
+    parser.add_argument('--images', default='images', help='images directory')
+    args = parser.parse_args()
+
+    # Derive filenames
+    build_dir = Path(args.build)
+    tex_file = args.tex or build_dir / Path(args.input).with_suffix(".tex").name
+    pdf_file = args.output or build_dir / Path(args.input).with_suffix(".pdf").name
+
+    metadata = build_tex(args.input, tex_file, template=args.template, bib_file=args.bib, filters=args.filters, journal_template=args.journal_template, filters_module=args.filters_module)
+
+    if args.pdf:
+        compile_pdf(tex_file, pdf_file, args.engine, args.build, args.images, bib_file=metadata.get('bibliography'), resource_path=metadata.get('resource_path'))
+
+
+if __name__ == '__main__':
+    main()