VALLONGOL/SXXXXXXX_MarkdownConverter
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

update format

Browse Source
This commit is contained in:
VALLONGOL 2025-07-22 14:48:55 +02:00
parent f3f2edae57
commit 4edfc33bdb
8 changed files with 95 additions and 21 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
.~lock.TemplateSumSample.docx#
View File

@ -1 +0,0 @@
Luca Vallongo,Win11_Dev/admin,Win11_Dev,18.06.2025 08:03,file:///C:/Users/admin/AppData/Roaming/LibreOffice/4;

BIN
TemplateSumSample - versione con numeri su titoli.docx Normal file
View File

Binary file not shown.

BIN
TemplateSumSample.docx
View File

Binary file not shown.

26
config/app_config.json
View File

@ -1,6 +1,6 @@
{ {
"last_markdown_file": "C:/src/____GitProjects/cpp_python_debug/doc/Italian-manual.md", "last_markdown_file": "C:/src/____GitProjects/radar_data_reader/doc/English-manual.md",
"last_selected_profile": "cpp_python_debug", "last_selected_profile": "radar_data_reader",
"profiles": { "profiles": {
"cpp_python_debug": { "cpp_python_debug": {
"template_path": "C:/src/____GitProjects/cpp_python_debug/doc/TemplateSumSample.docx", "template_path": "C:/src/____GitProjects/cpp_python_debug/doc/TemplateSumSample.docx",
@ -12,6 +12,28 @@
"%%DOC_REV%%": "A2", "%%DOC_REV%%": "A2",
"%%DOC_SECURITY%%": "INTERNAL" "%%DOC_SECURITY%%": "INTERNAL"
} }
},
"radar_data_reader": {
"template_path": "C:/src/____GitProjects/MarkdownConverter/TemplateSumSample.docx",
"values": {
"%%DOC_CUSTOMER%%": "INTERNAL",
"%%DOC_DATE%%": "22/07/2025",
"%%DOC_NUMBER%%": "90000002",
"%%DOC_PROJECT%%": "RADAR DATA READER",
"%%DOC_REV%%": "A",
"%%DOC_SECURITY%%": "INTERNAL"
}
},
"mark_converter": {
"template_path": "C:/src/____GitProjects/MarkdownConverter/TemplateSumSample.docx",
"values": {
"%%DOC_CUSTOMER%%": "INTERNO",
"%%DOC_DATE%%": "22/07/2025",
"%%DOC_NUMBER%%": "900000003",
"%%DOC_PROJECT%%": "MARK CONVERTER",
"%%DOC_REV%%": "A",
"%%DOC_SECURITY%%": "INTERNAL"
}
} }
} }
} }

BIN
doc/MARK_CONVERTER_SUM_900000003_A_20250722.docx Normal file
View File

Binary file not shown.

BIN
doc/MARK_CONVERTER_SUM_900000003_A_20250722.pdf Normal file
View File

Binary file not shown.

72
markdownconverter/core/core.py
View File

@ -208,19 +208,27 @@ def _convert_to_pdf(markdown_text: str, output_file: str, add_toc: bool):
log.info("Starting PDF conversion using pdfkit.") log.info("Starting PDF conversion using pdfkit.")
if config is None: if config is None:
raise FileNotFoundError("wkhtmltopdf executable not found. Cannot create PDF.") raise FileNotFoundError("wkhtmltopdf executable not found. Cannot create PDF.")
title = _get_document_title(markdown_text) title = _get_document_title(markdown_text)
content_without_title = markdown_text content_without_title = markdown_text
match = re.search(r"^\s*#+\s+(.+)\n?", markdown_text, re.MULTILINE) match = re.search(r"^\s*#+\s+(.+)\n?", markdown_text, re.MULTILINE)
if match: if match:
content_without_title = markdown_text[match.end() :] content_without_title = markdown_text[match.end() :]
md_converter = markdown.Markdown(extensions=["toc", "fenced_code", "tables"])
# Previous code:
# md_converter = markdown.Markdown(extensions=["toc", "fenced_code", "tables"])
# New code with 'nl2br' extension:
md_converter = markdown.Markdown(extensions=["toc", "fenced_code", "tables", "nl2br"])
html_body = md_converter.convert(content_without_title) html_body = md_converter.convert(content_without_title)
toc_html = "" toc_html = ""
if add_toc and hasattr(md_converter, "toc") and md_converter.toc: if add_toc and hasattr(md_converter, "toc") and md_converter.toc:
log.info("Generating Table of Contents for PDF.") log.info("Generating Table of Contents for PDF.")
toc_html = f"<h2>Table of Contents</h2>{md_converter.toc}<div style='page-break-after: always;'></div>" toc_html = f"<h2>Table of Contents</h2>{md_converter.toc}<div style='page-break-after: always;'></div>"
full_html = f'<!DOCTYPE html><html lang="en"><head><meta charset="UTF-8"><title>{title}</title><style>body{{font-family:sans-serif;}}h1,h2{{border-bottom:1px solid #eaecef;padding-bottom:.3em;}}</style></head><body><h1>{title}</h1>{toc_html}{html_body}</body></html>' full_html = f'<!DOCTYPE html><html lang="en"><head><meta charset="UTF-8"><title>{title}</title><style>body{{font-family:sans-serif;}}h1,h2{{border-bottom:1px solid #eaecef;padding-bottom:.3em;}}</style></head><body><h1>{title}</h1>{toc_html}{html_body}</body></html>'
pdf_options = {"encoding": "UTF-8", "enable-local-file-access": None} pdf_options = {"encoding": "UTF-8", "enable-local-file-access": None}
pdfkit.from_string( pdfkit.from_string(
full_html, output_file, configuration=config, options=pdf_options full_html, output_file, configuration=config, options=pdf_options
) )
@ -255,67 +263,99 @@ def _convert_to_docx(
rev_history_md, main_content_md = _split_markdown_by_revision_history(markdown_text) rev_history_md, main_content_md = _split_markdown_by_revision_history(markdown_text)
_add_revision_table(doc, rev_history_md) _add_revision_table(doc, rev_history_md)
temp_files = [] temp_files = []
pandoc_format = "markdown+hard_line_breaks"
try: try:
if main_content_md: if main_content_md:
content_for_pandoc = main_content_md content_for_pandoc = main_content_md
# Step 1: Remove the main H1 document title from the content to be processed.
# It's used for metadata, not for the main body's numbering.
match = re.search(r"^\s*#\s+(.+)\n?", content_for_pandoc, re.MULTILINE) match = re.search(r"^\s*#\s+(.+)\n?", content_for_pandoc, re.MULTILINE)
if match: if match:
log.info( log.info("Removing main H1 title from content body.")
"Removing main title from content to exclude it from DOCX TOC."
)
content_for_pandoc = content_for_pandoc[match.end() :] content_for_pandoc = content_for_pandoc[match.end() :]
log.info("Stripping manual numbering from headings.")
# Step 2: Strip any existing manual numbering from headings (e.g., "## 1. Title")
# to prevent double numbering when automatic numbering is applied.
log.info("Stripping manual numbering from headings for auto-numbering.")
content_for_pandoc = re.sub( content_for_pandoc = re.sub(
r"^(\s*#+)\s+[0-9\.]+\s+", r"^(\s*#+)\s+[0-9\.]+\s+",
r"\1 ", r"\1 ",
content_for_pandoc, content_for_pandoc,
flags=re.MULTILINE, flags=re.MULTILINE,
) )
pandoc_args = ["--shift-heading-level-by=-1"]
# Step 3: Configure Pandoc arguments for correct hierarchical numbering.
pandoc_args = [
# Enable automatic section numbering (e.g., 1, 1.1, 1.1.1).
"--number-sections",
# Shift heading levels up by one. This maps:
# ## (H2 in MD) -> Heading 1 in DOCX (numbered as 1, 2, ...)
# ### (H3 in MD) -> Heading 2 in DOCX (numbered as 1.1, 1.2, ...)
"--shift-heading-level-by=-1",
# Keep text left-aligned.
"--variable=justify:false",
]
if add_toc: if add_toc:
pandoc_args.append("--toc") pandoc_args.append("--toc")
log.info("Adding page break before Table of Contents.") log.info("Adding page break before Table of Contents.")
toc_placeholder_p = _find_placeholder_paragraph(doc, "%%DOC_TOC%%") toc_placeholder_p = _find_placeholder_paragraph(doc, "%%DOC_TOC%%")
toc_placeholder_p.insert_paragraph_before().add_run().add_break( # Insert a page break before the TOC for better formatting.
WD_BREAK.PAGE if toc_placeholder_p:
) toc_placeholder_p.insert_paragraph_before().add_run().add_break(
WD_BREAK.PAGE
)
with tempfile.NamedTemporaryFile( with tempfile.NamedTemporaryFile(
delete=False, suffix=".docx" delete=False, suffix=".docx"
) as temp_file: ) as temp_file:
pypandoc.convert_text( pypandoc.convert_text(
content_for_pandoc, content_for_pandoc,
"docx", "docx",
format="md", format=pandoc_format,
extra_args=pandoc_args, extra_args=pandoc_args,
outputfile=temp_file.name, outputfile=temp_file.name,
) )
temp_files.append(temp_file.name) temp_files.append(temp_file.name)
_insert_docx_at_paragraph(toc_placeholder_p, temp_file.name) if toc_placeholder_p:
_insert_docx_at_paragraph(toc_placeholder_p, temp_file.name)
# The main content is now part of the generated TOC doc, so remove the placeholder.
_remove_paragraph(_find_placeholder_paragraph(doc, "%%DOC_CONTENT%%")) _remove_paragraph(_find_placeholder_paragraph(doc, "%%DOC_CONTENT%%"))
else: else:
# If no TOC, just insert the content at its placeholder.
log.info("Adding page break before main content.") log.info("Adding page break before main content.")
content_placeholder_p = _find_placeholder_paragraph( content_placeholder_p = _find_placeholder_paragraph(
doc, "%%DOC_CONTENT%%" doc, "%%DOC_CONTENT%%"
) )
content_placeholder_p.insert_paragraph_before().add_run().add_break( if content_placeholder_p:
WD_BREAK.PAGE content_placeholder_p.insert_paragraph_before().add_run().add_break(
) WD_BREAK.PAGE
)
with tempfile.NamedTemporaryFile( with tempfile.NamedTemporaryFile(
delete=False, suffix=".docx" delete=False, suffix=".docx"
) as temp_file: ) as temp_file:
# We don't add '--toc' to pandoc_args here.
pypandoc.convert_text( pypandoc.convert_text(
content_for_pandoc, content_for_pandoc,
"docx", "docx",
format="md", format=pandoc_format,
extra_args=pandoc_args, extra_args=pandoc_args,
outputfile=temp_file.name, outputfile=temp_file.name,
) )
temp_files.append(temp_file.name) temp_files.append(temp_file.name)
_insert_docx_at_paragraph(content_placeholder_p, temp_file.name) if content_placeholder_p:
_insert_docx_at_paragraph(content_placeholder_p, temp_file.name)
# TOC placeholder is not used, so remove it.
_remove_paragraph(_find_placeholder_paragraph(doc, "%%DOC_TOC%%")) _remove_paragraph(_find_placeholder_paragraph(doc, "%%DOC_TOC%%"))
else: else:
# If there is no main content, remove both placeholders.
_remove_paragraph(_find_placeholder_paragraph(doc, "%%DOC_TOC%%")) _remove_paragraph(_find_placeholder_paragraph(doc, "%%DOC_TOC%%"))
_remove_paragraph(_find_placeholder_paragraph(doc, "%%DOC_CONTENT%%")) _remove_paragraph(_find_placeholder_paragraph(doc, "%%DOC_CONTENT%%"))
doc.save(output_file) doc.save(output_file)
log.info(f"Document successfully created at {output_file}") log.info(f"Document successfully created at {output_file}")
finally: finally:

17
markdownconverter/gui/gui.py
View File

@ -149,13 +149,19 @@ class MarkdownConverterApp:
self.dynamic_entry_vars = {} self.dynamic_entry_vars = {}
self.loaded_profile_name = "" self.loaded_profile_name = ""
self.selected_file = StringVar(value=self.config.get(KEY_LAST_MARKDOWN, "")) self.selected_file = StringVar(value=self.config.get(KEY_LAST_MARKDOWN, ""))
self.active_profile_name = StringVar() # Inizializzata vuota
# --- NEW CODE ---
# Add a trace to the StringVar. Whenever its value is written,
# the _on_selected_file_change callback will be executed.
self.selected_file.trace_add("write", self._on_selected_file_change)
self.active_profile_name = StringVar() # Initialized empty
self.add_toc_var = BooleanVar(value=True) self.add_toc_var = BooleanVar(value=True)
self.docx_output_path = StringVar() self.docx_output_path = StringVar()
self.pdf_direct_output_path = StringVar() self.pdf_direct_output_path = StringVar()
self.pdf_from_docx_output_path = StringVar() self.pdf_from_docx_output_path = StringVar()
self._build_ui() self._build_ui()
self.update_profile_combobox() # Questo imposterà active_profile_name self.update_profile_combobox() # This will set active_profile_name
self.root.protocol("WM_DELETE_WINDOW", self._on_closing) self.root.protocol("WM_DELETE_WINDOW", self._on_closing)
def _setup_logging(self): def _setup_logging(self):
@ -345,6 +351,13 @@ class MarkdownConverterApp:
shutdown_logging_system() shutdown_logging_system()
self.root.destroy() self.root.destroy()
def _on_selected_file_change(self, *args):
"""
Callback function that is triggered whenever the self.selected_file
StringVar is written to. It ensures the output paths are updated.
"""
self._update_output_paths()
def run_app(): def run_app():
root = tb.Window(themename="sandstone") root = tb.Window(themename="sandstone")
app = MarkdownConverterApp(root) app = MarkdownConverterApp(root)