Convert DOC(X) to HTML, set up GitHub actions (#3)

lemontree210 · web-flow · commit f407e5a780f2 · 2025-08-20T10:30:46.000+03:00
* Implement DOC(X) to HTML conversion with customizable style mapping
* Set up GitHub Actions workflow, Codecov configuration, and Dependabot
diff --git a/.github/dependabot.yml b/.github/dependabot.yml
@@ -0,0 +1,9 @@
+# For future reference - the options are specified here:
+# https://docs.github.com/en/code-security/dependabot/dependabot-version-updates/configuration-options-for-the-dependabot.yml-file
+
+version: 2
+updates:
+  - package-ecosystem: "pip"
+    directory: "/"
+    schedule:
+      interval: "monthly"
diff --git a/.github/workflows/pytest.yml b/.github/workflows/pytest.yml
@@ -0,0 +1,31 @@
+name: tests
+
+on: [push]
+
+jobs:
+  test:
+    runs-on: ubuntu-22.04
+    timeout-minutes: 5
+
+    steps:
+      - uses: actions/checkout@v3
+        with:
+          fetch-depth: 0
+      - name: Set up Python
+        uses: actions/setup-python@v2
+        with:
+          python-version: "3.9"
+      - name: install deps
+        run: |
+          python -m pip install --upgrade pip
+          pip install poetry
+          poetry install
+      - name: run tests
+        run: |
+          poetry run pytest -v --tb=short --cov=./ --cov-report=xml
+      - name: Upload coverage reports to Codecov
+        uses: codecov/codecov-action@v5
+        with:
+          token: ${{ secrets.CODECOV_TOKEN }}
+          slug: lemontree210/tinybear
+          fail_ci_if_error: true
diff --git a/.gitignore b/.gitignore
@@ -191,4 +191,11 @@ cython_debug/
 #  exclude from AI features like autocomplete and code analysis. Recommended for sensitive data
 #  refer to https://docs.cursor.com/context/ignore-files
 .cursorignore
-.cursorindexingignore
+.cursorindexingignore
+
+# QODO AI assistant
+/.qodo/
+
+# Directories for user's input files and programs' output files
+/input/
+/output/
diff --git a/.pre-commit-config.yaml b/.pre-commit-config.yaml
@@ -5,12 +5,12 @@ repos:
     -   id: black
         language_version: python3.9
 -   repo: https://github.com/pre-commit/mirrors-mypy
-    rev: v1.16.1
+    rev: v1.17.1
     hooks:
       - id: mypy
 -   repo: https://github.com/astral-sh/ruff-pre-commit
     # Ruff version.
-    rev: 'v0.12.0'
+    rev: 'v0.12.7'
     hooks:
     -   id: ruff
         name: ruff
diff --git a/README.md b/README.md
@@ -1,2 +1,4 @@
 # tinybear
-Where you don't need pandas yet. Tools to work with TXT, CSV, Excel etc. 
+Where you don't need pandas yet. Tools to work with TXT, CSV, Excel etc.
+
+[![codecov](https://codecov.io/gh/lemontree210/tinybear/graph/badge.svg?token=S0XIMP99YU)](https://codecov.io/gh/lemontree210/tinybear)
diff --git a/codecov.yml b/codecov.yml
@@ -0,0 +1,6 @@
+coverage:
+  status:
+    project:
+      default:
+        target: auto
+        threshold: 1%
diff --git a/poetry.lock b/poetry.lock
diff --git a/pyproject.toml b/pyproject.toml
@@ -18,7 +18,7 @@ ignore_errors = true
 
 [tool.poetry]
 name = "tinybear"
-version = "0.2.0"
+version = "0.3.0"
 description = "Where you don't need pandas yet. Tools to work with TXT, CSV, HTML, XLSX etc."
 authors = ["Dmitry K <58207913+lemontree210@users.noreply.github.com>"]
 readme = "README.md"
@@ -30,11 +30,12 @@ html5lib = "^1.1"
 openpyxl = "^3.1.5"
 pyyaml = "^6.0.2"
 toml = "^0.10.2"
+mammoth = "^1.10.0"
 
 [tool.poetry.group.dev.dependencies]
 black = "^25.1.0"
-mypy = "^1.16.1"
-ruff = "^0.12.0"
+mypy = "^1.17.1"
+ruff = "^0.12.7"
 pre-commit = "^4.2.0"
 pytest = "^8.4.1"
 pytest-cov = "^6.2.1"
diff --git a/tests/test_data/html/from_docx/default_style.docx b/tests/test_data/html/from_docx/default_style.docx
diff --git a/tests/test_helpers.py b/tests/test_helpers.py
@@ -1,7 +1,4 @@
-import pytest
-
 from tests.helpers import check_existence_of_output_csv_file_and_compare_with_gold_standard
-
 from tests.paths import DIR_WITH_TEST_FILES
 from tinybear.csv_xls import write_csv
 
diff --git a/tests/test_html_from_docx.py b/tests/test_html_from_docx.py
@@ -0,0 +1,97 @@
+import re
+
+from tests.paths import DIR_WITH_TEST_FILES
+from tinybear.html.from_docx import read_from_doc, convert_file_from_doc, convert_all_docs
+
+CUSTOM_STYLE_MAP = """
+b => b
+i => i
+p[style-name='Title'] => h1
+p[style-name='Heading1'] => h2
+p[style-name='Heading 1'] => h2
+p[style-name='Heading2'] => h3
+p[style-name='Heading 2'] => h3
+p[style-name='Heading3'] => h4
+p[style-name='Heading 3'] => h4
+p[style-name='Heading4'] => strong
+p[style-name='Heading 4'] => strong
+"""
+
+TEST_DOCS_DIR = DIR_WITH_TEST_FILES / "html" / "from_docx"
+TEST_DOCX_FILE = TEST_DOCS_DIR / "default_style.docx"
+
+
+def test_read_from_doc():
+    html = read_from_doc(TEST_DOCX_FILE)
+    patterns = [
+        (r"<h1>This is the document title</h1>", "Title -> h1"),
+        (r"<h1>Heading level 1</h1>", "Heading1 -> h1"),
+        (r"<h2>Heading level 2</h2>", "Heading2 -> h2"),
+        (r"<h3>Heading level 3</h3>", "Heading3 -> h3"),
+        (r"<h4>Heading level 4</h4>", "Heading4 -> h4"),
+        (r"<strong>bold text</strong>", "Bold text -> <strong>"),
+        (r"<em>italic text</em>", "Italic text -> <em>"),
+        (
+            r"<strong><em>bold italic text</em></strong>|<em><strong>bold italic text</strong></em>",
+            "Bold italic text -> <strong><em> or <em><strong>",
+        ),
+    ]
+    for pattern, desc in patterns:
+        assert re.search(pattern, html), f"Missing or incorrect: {desc}"
+
+
+def test_read_from_doc_with_custom_style_map():
+
+    html = read_from_doc(TEST_DOCX_FILE, style_map=CUSTOM_STYLE_MAP)
+    patterns = [
+        (r"<h1>This is the document title</h1>", "Title -> h1"),
+        (r"<h2>Heading level 1</h2>", "Heading1 -> h2"),
+        (r"<h3>Heading level 2</h3>", "Heading2 -> h3"),
+        (r"<h4>Heading level 3</h4>", "Heading3 -> h4"),
+        (r"<strong>Heading level 4</strong>", "Heading4 -> strong"),
+        (r"<b>bold text</b>", "Bold text -> <b>"),
+        (r"<i>italic text</i>", "Italic text -> <i>"),
+        (
+            r"<b><i>bold italic text</i></b>|<i><b>bold italic text</b></i>",
+            "Bold italic text -> <b><i> or <i><b>",
+        ),
+    ]
+    for pattern, desc in patterns:
+        assert re.search(pattern, html), f"Missing or incorrect: {desc}"
+
+
+def test_convert_file_from_doc(tmp_path):
+    output_path = convert_file_from_doc(TEST_DOCX_FILE, output_dir=tmp_path, print_html=False)
+    assert output_path.exists()
+    html = output_path.read_text(encoding="utf-8")
+    # Spot check for a couple of tags
+    assert "<h1>Heading level 1</h1>" in html
+    assert "<strong>bold text</strong>" in html
+
+
+def test_convert_file_from_doc_with_custom_style_map(tmp_path):
+    output_path = convert_file_from_doc(
+        TEST_DOCX_FILE, output_dir=tmp_path, print_html=False, style_map=CUSTOM_STYLE_MAP
+    )
+    assert output_path.exists()
+    html = output_path.read_text(encoding="utf-8")
+    # Check for custom mapping effect
+    assert "<h2>Heading level 1</h2>" in html or "<h2>Heading level 1" in html
+    assert "<b>bold text</b>" in html
+
+
+def test_convert_file_from_doc_prints_html(tmp_path, caplog):
+    with caplog.at_level("INFO"):
+        output_path = convert_file_from_doc(TEST_DOCX_FILE, output_dir=tmp_path, print_html=True)
+    assert output_path.exists()
+    # Check that HTML was logged
+    assert any("document title" in message for message in caplog.messages)
+
+
+def test_convert_all_docs_logs_conversion(tmp_path, caplog):
+    with caplog.at_level("INFO"):
+        convert_all_docs(input_dir=TEST_DOCS_DIR, output_dir=tmp_path, print_html=False)
+    # Check that "Converting" and the file name are in the logs
+    assert any(
+        "Converting" in message and TEST_DOCX_FILE.name in message for message in caplog.messages
+    )
diff --git a/tests/test_json_toml_yaml.py b/tests/test_json_toml_yaml.py
@@ -2,10 +2,7 @@
 
 from tests.paths import DIR_WITH_TEST_FILES
 from tinybear.exceptions import ParsingError
-from tinybear.json_toml_yaml import (
-    check_yaml_file,
-    read_json_toml_yaml,
-)
+from tinybear.json_toml_yaml import check_yaml_file, read_json_toml_yaml
 
 
 def test_check_yaml_file_passes_with_valid_data():
diff --git a/tinybear/_paths.py b/tinybear/_paths.py
@@ -0,0 +1,5 @@
+from pathlib import Path
+
+DEFAULT_INPUT_DIR = Path("..") / ".." / "input"
+
+DEFAULT_OUTPUT_DIR = Path("..") / ".." / "output"
diff --git a/tinybear/html/from_docx.py b/tinybear/html/from_docx.py
@@ -0,0 +1,72 @@
+import logging
+from pathlib import Path
+
+import mammoth
+
+from tinybear._paths import DEFAULT_INPUT_DIR, DEFAULT_OUTPUT_DIR
+
+logging.basicConfig(level=logging.INFO)
+
+DEFAULT_STYLE_MAP = """
+b => strong
+i => em
+p[style-name='Title'] => h1
+p[style-name='Heading1'] => h1
+p[style-name='Heading 1'] => h1
+p[style-name='Heading2'] => h2
+p[style-name='Heading 2'] => h2
+p[style-name='Heading3'] => h3
+p[style-name='Heading 3'] => h3
+p[style-name='Heading4'] => h4
+p[style-name='Heading 4'] => h4
+"""
+
+
+def convert_file_from_doc(
+    path_to_file: Path,
+    output_dir: Path = DEFAULT_OUTPUT_DIR,
+    style_map: str = DEFAULT_STYLE_MAP,
+    print_html: bool = True,
+) -> Path:
+    """Read from DOC(x) file, write to HTML file, return its path."""
+
+    html = read_from_doc(path_to_file=path_to_file, style_map=style_map)
+
+    if print_html:
+        logging.info(html)
+
+    output_path = output_dir / f"{path_to_file.stem}.html"
+
+    with output_path.open(mode="w", encoding="utf-8") as output_file:
+        output_file.write(html)
+
+    return output_path
+
+
+def convert_all_docs(
+    input_dir: Path = DEFAULT_INPUT_DIR,
+    output_dir: Path = DEFAULT_OUTPUT_DIR,
+    print_html: bool = True,
+) -> None:
+    """Converts all .DOC(x) files in a directory."""
+    if not output_dir.exists():
+        output_dir.mkdir()
+
+    for pattern in ("*.doc", "*.docx"):
+        for file in input_dir.glob(pattern):
+            logging.info(f"Converting {file.name}")
+            convert_file_from_doc(path_to_file=file, output_dir=output_dir, print_html=print_html)
+
+
+def read_from_doc(
+    path_to_file: Path,
+    style_map: str = DEFAULT_STYLE_MAP,
+) -> str:
+    """Read binary content from doc file and produce string HTML."""
+    with path_to_file.open(mode="rb") as docx_file:
+        result = mammoth.convert_to_html(docx_file, style_map=style_map)
+        return result.value
+
+
+if __name__ == "__main__":
+    convert_all_docs()  # pragma: no cover
