v0.5.2

Что то сделал

md2gost/pipeline.py

@@ -9,7 +9,7 @@ import subprocess
 import traceback
 from dataclasses import dataclass
 from datetime import datetime
-from getpass import getuser
+from pathlib import Path
 from typing import Callable
 
 from docx import Document
@@ -41,6 +41,10 @@ class ConvertRequest:
     hr_pagebreak: bool = False
     title: str | None = None
     assignment: str | None = None
+    student: str | None = None
+    group: str | None = None
+    # Auto-build title from info_conv.yaml / ```title (off by default).
+    auto_title: bool = False
     check: bool = False
     check_only: bool = False
     strict: bool = False
@@ -58,6 +62,15 @@ class ConvertRequest:
     table_repeat_header: bool = False
     # PAGE field start on body section; None = continuous from document start.
     page_number_start: int | None = None
+    # DOCX File → Info; None = take from md2gost.user.json (see doc_metadata).
+    doc_author_source: str | None = None
+    doc_author: str | None = None
+    doc_last_modified_by: str | None = None
+    doc_title: str | None = None
+    doc_subject: str | None = None
+    doc_keywords: str | None = None
+    doc_comments: str | None = None
+    doc_category: str | None = None
 
 
 @dataclass
@@ -127,16 +140,33 @@ def _apply_page_offset(document, req: ConvertRequest, *, had_title: bool, had_as
     from .page_geometry import apply_page_number_start
 
     start = getattr(req, "page_number_start", None)
+    start_i: int | None
     if start is None:
-        return
-    try:
-        start_i = int(start)
-    except (TypeError, ValueError):
-        return
+        start_i = None
+    else:
+        try:
+            start_i = int(start)
+        except (TypeError, ValueError):
+            start_i = None
     front = int(bool(had_title)) + int(bool(had_assignment))
+    # Always strip copied w:pgNumType/@w:start (landscape sections); optional body restart.
     apply_page_number_start(document, start_i, front_sections=front)
 
 
+def _page_offset_args(req: ConvertRequest, *, had_title: bool, had_assignment: bool) -> tuple[int | None, int]:
+    """Return (page_number_start, front_sections) for post-Word patch."""
+    start = getattr(req, "page_number_start", None)
+    if start is None:
+        start_i = None
+    else:
+        try:
+            start_i = int(start)
+        except (TypeError, ValueError):
+            start_i = None
+    front = int(bool(had_title)) + int(bool(had_assignment))
+    return start_i, front
+
+
 def convert(req: ConvertRequest, log: LogFn | None = None) -> ConvertResult:
     """Run check and/or conversion. Does not re-raise; errors go into ConvertResult."""
     emit: LogFn = log if log is not None else print
@@ -154,6 +184,24 @@ def convert(req: ConvertRequest, log: LogFn | None = None) -> ConvertResult:
         emit(report)
         return ConvertResult(True, 0, check_report=report, message=report)
 
+    # DOCX → Markdown (word2md) when input is .docx without --check-pages
+    if filename.lower().endswith(".docx"):
+        from word2md import ImportRequest, convert_docx
+
+        out = (req.output or "").strip() or None
+        if out and out.lower().endswith(".docx"):
+            out = str(Path(filename).with_suffix(".md"))
+        result = convert_docx(
+            ImportRequest(filename=filename, output=out),
+            log=emit,
+        )
+        return ConvertResult(
+            result.ok,
+            result.exit_code,
+            output_path=result.output_path,
+            message=result.message,
+        )
+
     if not filename:
         return fail(2, "Укажите исходный markdown-файл")
     if not filename.lower().endswith(".md"):
@@ -192,10 +240,57 @@ def convert(req: ConvertRequest, log: LogFn | None = None) -> ConvertResult:
     with open(filename, encoding="utf-8") as f:
         md_text = f.read()
 
+    from .title_page import (
+        build_title_docx,
+        load_info_conv,
+        merge_title_meta,
+        parse_and_strip_title_fence,
+        should_generate_title,
+    )
+    from .user_profile import load_user_profile
+
+    fence_fields, body_md = parse_and_strip_title_fence(md_text)
+    yaml_fields = load_info_conv(md_dir)
+    generated_title_path: str | None = None
+    title_path = (req.title or "").strip() or None
+
+    if not output:
+        output = default_output_path(filename)
+
+    if should_generate_title(
+        explicit_title=title_path,
+        fence_fields=fence_fields,
+        md_dir=md_dir,
+        enabled=bool(req.auto_title),
+    ):
+        profile = load_user_profile()
+        student = (req.student or "").strip() or profile.student
+        group = (req.group or "").strip() or profile.group
+        if not student or not group:
+            return fail(
+                2,
+                "Для генерации титула нужны ФИО и группа студента "
+                "(GUI: Настройки → Студент…, или CLI: --student / --group).",
+            )
+        meta = merge_title_meta(
+            yaml_fields=yaml_fields,
+            fence_fields=fence_fields,
+            student=student,
+            group=group,
+        )
+        out_dir = os.path.dirname(os.path.abspath(output)) or md_dir
+        generated_title_path = os.path.join(out_dir, ".md2gost_title.docx")
+        try:
+            build_title_docx(meta, generated_title_path)
+            title_path = generated_title_path
+            emit(f"Титульный лист: {generated_title_path}")
+        except Exception as exc:
+            return fail(1, f"Не удалось сгенерировать титул: {exc}")
+
     check_report = ""
     if req.check or req.check_only:
         issues = check_markdown(
-            md_text,
+            body_md,
             req.doc_type,
             table_continuation=req.table_continuation,
             listing_continuation=req.listing_continuation,
@@ -211,9 +306,6 @@ def convert(req: ConvertRequest, log: LogFn | None = None) -> ConvertResult:
                 message=check_report,
             )
 
-    if not output:
-        output = default_output_path(filename)
-
     template = (req.template or "").strip() or default_template_path()
 
     handler = _CallbackLogHandler(emit)
@@ -236,11 +328,12 @@ def convert(req: ConvertRequest, log: LogFn | None = None) -> ConvertResult:
             listing_continuation=req.listing_continuation,
             hr_pagebreak=req.hr_pagebreak,
             styles_path=req.styles_path or None,
+            markdown_text=body_md,
         )
         converter.convert()
         document = converter.document
 
-        if req.title or req.assignment:
+        if title_path or req.assignment:
             try:
                 from docxcompose.composer import Composer
             except ImportError:
@@ -256,8 +349,8 @@ def convert(req: ConvertRequest, log: LogFn | None = None) -> ConvertResult:
                     body.remove(child)
 
             composer = Composer(shell)
-            if req.title:
-                composer.append(Document(req.title))
+            if title_path:
+                composer.append(Document(title_path))
                 shell.add_page_break()
             if req.assignment:
                 composer.append(Document(req.assignment))
@@ -267,19 +360,36 @@ def convert(req: ConvertRequest, log: LogFn | None = None) -> ConvertResult:
             apply_style_config(document, style_cfg)
             _fix_front_matter_after_compose(
                 document,
-                had_title=bool(req.title),
+                had_title=bool(title_path),
                 had_assignment=bool(req.assignment),
             )
 
         _apply_page_offset(
             document,
             req,
-            had_title=bool(req.title),
+            had_title=bool(title_path),
             had_assignment=bool(req.assignment),
         )
 
-        document.core_properties.author = getuser()
-        document.core_properties.comments = "Создано при помощи md2gost (ТЗ МИРЭА)"
+        from .doc_metadata import apply_document_metadata, resolve_document_metadata
+        from .user_profile import load_user_profile as _load_user_profile
+
+        profile = _load_user_profile()
+        apply_document_metadata(
+            document,
+            resolve_document_metadata(
+                stored=profile.metadata,
+                student=(req.student or "").strip() or profile.student,
+                author_source=req.doc_author_source,
+                author=req.doc_author,
+                last_modified_by=req.doc_last_modified_by,
+                title=req.doc_title,
+                subject=req.doc_subject,
+                keywords=req.doc_keywords,
+                comments=req.doc_comments,
+                category=req.doc_category,
+            ),
+        )
         try:
             document.save(output)
         except PermissionError:
@@ -297,12 +407,19 @@ def convert(req: ConvertRequest, log: LogFn | None = None) -> ConvertResult:
         root_log.removeHandler(handler)
         attached_diag.removeHandler(handler)
         attached_diag.setLevel(prev_diag_level)
+        if generated_title_path and os.path.isfile(generated_title_path):
+            try:
+                os.remove(generated_title_path)
+            except OSError:
+                pass
 
     abs_out = os.path.abspath(output)
     emit(f"Generated document: {abs_out}")
 
     if req.table_continuation == "word" or req.listing_continuation == "word":
         from .word_fix import fix_continuations
+        from .page_geometry import patch_docx_page_starts
+
         fix = fix_continuations(
             abs_out,
             tables=(req.table_continuation == "word"),
@@ -317,6 +434,16 @@ def convert(req: ConvertRequest, log: LogFn | None = None) -> ConvertResult:
             check_report = (
                 (check_report + "\n" + fix.message).strip() if check_report else fix.message
             )
+        # Word Save often rewrites w:pgNumType/@w:start=\"1\" on every section — strip again.
+        start_i, front = _page_offset_args(
+            req,
+            had_title=bool(title_path),
+            had_assignment=bool(req.assignment),
+        )
+        try:
+            patch_docx_page_starts(abs_out, start_i, front_sections=front)
+        except Exception as exc:
+            emit(f"Не удалось восстановить сквозную нумерацию после Word: {exc}")
 
     if req.check_pages:
         from .page_fill_check import check_docx_page_fill, format_page_fill_report