qparse 0.1.0__tar.gz → 0.1.2__tar.gz

{qparse-0.1.0 → qparse-0.1.2}/MANIFEST.in

@@ -1,6 +1,5 @@
 include README.md
 include LICENSE
-include requirements.txt
 recursive-include qparse/render_option *.json *.md *.docx
 global-exclude __pycache__ *.py[cod]
 prune qparse/docx_render/bak

{qparse-0.1.0/qparse.egg-info → qparse-0.1.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: qparse
-Version: 0.1.0
+Version: 0.1.2
 Summary: Structured Markdown lesson plans to DOCX, with .qmd pack/unpack tooling.
 Author: hanbuhuai
 License: MIT

{qparse-0.1.0 → qparse-0.1.2}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "qparse"
-version = "0.1.0"
+version = "0.1.2"
 description = "Structured Markdown lesson plans to DOCX, with .qmd pack/unpack tooling."
 readme = "README.md"
 requires-python = ">=3.9"
@@ -43,16 +43,18 @@ Repository = "https://github.com/hanbuhuai/qparse"
 Issues = "https://github.com/hanbuhuai/qparse/issues"
 
 [project.scripts]
-qmd = "qmd_cli:main"
+qmd = "qparse.qmd_cli:main"
 
 [tool.setuptools]
 include-package-data = true
-py-modules = ["qmd_cli"]
 
 [tool.setuptools.packages.find]
 where = ["."]
 include = ["qparse*"]
-exclude = ["qparse.docx_render.bak", "qparse.docx_render.bak.*"]
+exclude = [
+  "qparse.docx_render.bak",
+  "qparse.docx_render.bak.*",
+]
 
 [tool.setuptools.package-data]
 qparse = [

{qparse-0.1.0 → qparse-0.1.2}/qparse/__init__.py

@@ -4,7 +4,7 @@ from .markdwon_render import MarkdwonRender
 from .qmd_packer import QmdPacker
 from .qmd_unpacker import QmdUnpacker
 
-__version__ = "0.1.0"
+__version__ = "0.1.2"
 
 __all__ = [
     "MarkdownLoader",

qparse-0.1.2/qparse/__main__.py

@@ -0,0 +1,7 @@
+# -*- coding: utf-8 -*-
+"""支持 python -m qparse。"""
+
+from .qmd_cli import main
+
+if __name__ == "__main__":
+    main()

{qparse-0.1.0 → qparse-0.1.2}/qparse/docx_render/docx_render.py

@@ -2,9 +2,8 @@
 
 from pathlib import Path
 from shutil import copy2, rmtree
-from uuid import uuid4
+from tempfile import mkdtemp
 from qparse.markdwon_document import *
-from typing import List
 from .write_buffer import *
 
 class DocxRender():
@@ -17,13 +16,9 @@ class DocxRender():
         self._run_time_dir = None
 
     def __enter__(self):
-        self._run_time_dir = self.src.parent.joinpath(
-            ".qmd_runtime",
-            uuid4().hex
-        )
-        self._run_time_dir.mkdir(parents=True, exist_ok=True)
+        # 用系统临时目录，避免中文工作区路径让 Windows pandoc 找不到图片
+        self._run_time_dir = Path(mkdtemp(prefix="qmd_runtime_"))
         self.render_buffer = DocumentBuffer(self)
-        
         return self
 
     def __exit__(self, exc_type, exc_value, traceback):
@@ -36,10 +31,7 @@ class DocxRender():
     @property
     def run_time_dir(self)->Path:
         if self._run_time_dir is None:
-            self._run_time_dir = self.src.parent.joinpath(
-                ".qmd_runtime",
-                uuid4().hex
-            )
+            self._run_time_dir = Path(mkdtemp(prefix="qmd_runtime_"))
         return self._run_time_dir
     @property
     def dist(self):

{qparse-0.1.0 → qparse-0.1.2}/qparse/docx_render/write_buffer.py

@@ -2,6 +2,7 @@
 from __future__ import annotations
 from typing import List,Union
 from pathlib import Path
+import os
 import re
 import pypandoc
 from docxcompose.composer import Composer
@@ -12,6 +13,7 @@ from docx.oxml import OxmlElement
 from docx.oxml.ns import qn
 from docx.enum.text import WD_ALIGN_PARAGRAPH
 from docx.shared import Inches
+from qparse.utils.path_resolve import rewrite_local_images_for_pandoc
 
 class BaseBuffer():
     
@@ -29,9 +31,42 @@ class BaseBuffer():
     def create_docx_file_path(self):
         return self.create_temp_file_path(f".{id(self)}.docx")
     
+    def _localize_images(self, text: str) -> str:
+        cache = getattr(self._render, "_pandoc_image_cache", None)
+        if cache is None:
+            cache = {}
+            self._render._pandoc_image_cache = cache
+        return rewrite_local_images_for_pandoc(text, self._render.run_time_dir, cache)
+
+    def _pandoc_extra_args(self, with_reference: bool = False):
+        runtime = Path(self._render.run_time_dir).resolve()
+        args = [
+            "--mathjax",
+            "--no-highlight",
+            f"--resource-path={runtime}",
+        ]
+        if with_reference:
+            args.append(f"--reference-doc={Path(self.referance_path).as_posix()}")
+        return args
+
+    def _convert_with_pandoc(self, source_file: Path, outputfile: Path, fmt: str, extra_args):
+        old_cwd = os.getcwd()
+        runtime = Path(self._render.run_time_dir).resolve()
+        try:
+            os.chdir(str(runtime))
+            pypandoc.convert_file(
+                source_file=Path(source_file).name,
+                to="docx",
+                format=fmt,
+                outputfile=str(Path(outputfile).resolve()),
+                extra_args=extra_args,
+            )
+        finally:
+            os.chdir(old_cwd)
+
     def write_to_text_file(self):
         fpath= self.create_temp_file_path(".md")
-        fpath.write_text(self.text,encoding='utf-8')
+        fpath.write_text(self._localize_images(self.text), encoding='utf-8')
         return fpath
     def _restore_outer_blank_lines(self, docx_path):
         lines = self.text.splitlines()
@@ -59,16 +94,11 @@ class BaseBuffer():
     def write_to_docx_file(self):
         temp_md_file_path = self.write_to_text_file()
         fpath= self.create_temp_file_path(".docx")
-        pypandoc.convert_file(
-            source_file=temp_md_file_path.as_posix(),
-            to="docx",
-            format="markdown+tex_math_dollars+hard_line_breaks",
-            outputfile=fpath.as_posix(),
-            extra_args=[
-                "--mathjax",
-                "--no-highlight",
-                f"--reference-doc={Path(self.referance_path).as_posix()}"
-            ]
+        self._convert_with_pandoc(
+            temp_md_file_path,
+            fpath,
+            "markdown+tex_math_dollars+hard_line_breaks",
+            self._pandoc_extra_args(with_reference=True),
         )
         self._restore_outer_blank_lines(fpath)
         return fpath
@@ -154,16 +184,11 @@ class MarkdwonTextBuffer(BaseBuffer):
     def write_to_docx_file(self):
         temp_md_file_path = self.write_to_text_file()
         fpath= self.create_temp_file_path(".docx")
-        pypandoc.convert_file(
-            source_file=temp_md_file_path.as_posix(),
-            to="docx",
-            format="markdown+tex_math_dollars+hard_line_breaks",
-            outputfile=fpath.as_posix(),
-            extra_args=[
-                "--mathjax",
-                "--no-highlight",
-                f"--reference-doc={Path(self.referance_path).as_posix()}"
-            ]
+        self._convert_with_pandoc(
+            temp_md_file_path,
+            fpath,
+            "markdown+tex_math_dollars+hard_line_breaks",
+            self._pandoc_extra_args(with_reference=True),
         )
         self._restore_outer_blank_lines(fpath)
         self._adjust_tables(fpath)
@@ -196,12 +221,7 @@ class HtmlTextBuffer(MarkdwonTextBuffer):
     
     def write_to_text_file(self):
         fpath= self.create_temp_file_path(".html")
-        fpath.write_text(self.text,encoding='utf-8')
-        return fpath
-
-    def write_to_text_file(self):
-        fpath= self.create_temp_file_path(".html")
-        fpath.write_text(self.text,encoding='utf-8')
+        fpath.write_text(self._localize_images(self.text), encoding='utf-8')
         return fpath
 
     def write_to_docx_file(self):
@@ -214,7 +234,7 @@ class HtmlTextBuffer(MarkdwonTextBuffer):
             to="docx",
             format="html+tex_math_dollars",
             outputfile=fpath.as_posix(),
-            extra_args=["--mathjax", "--no-highlight"]
+            extra_args=self._pandoc_extra_args(with_reference=False),
         )
         return fpath
 class TableHtmlTextBuffer(HtmlTextBuffer):
@@ -286,16 +306,11 @@ class TableHtmlTextBuffer(HtmlTextBuffer):
     def write_to_docx_file(self):
         temp_html_file_path = self.write_to_text_file()
         fpath = self.create_docx_file_path()
-        pypandoc.convert_file(
-            source_file=temp_html_file_path.as_posix(),
-            to="docx",
-            format="html+tex_math_dollars",
-            outputfile=fpath.as_posix(),
-            extra_args=[
-                "--mathjax",
-                "--no-highlight",
-                f"--reference-doc={Path(self.referance_path).as_posix()}"
-            ]
+        self._convert_with_pandoc(
+            temp_html_file_path,
+            fpath,
+            "html+tex_math_dollars",
+            self._pandoc_extra_args(with_reference=True),
         )
         self._adjust_docx(fpath)
         return fpath

{qparse-0.1.0 → qparse-0.1.2}/qparse/markdwon_document/nodes/img_node.py

@@ -3,6 +3,7 @@ from bs4 import BeautifulSoup,element
 from typing import Union
 import copy
 from .base_node import BaseNode
+from qparse.utils.path_resolve import to_pandoc_local_url
 
 class ImgNode(BaseNode):
     def __init__(self, node, render_option):
@@ -14,7 +15,11 @@ class ImgNode(BaseNode):
         return None
     
     def dump_soup(self):
-        return copy.deepcopy(self._soup)
+        soup = copy.deepcopy(self._soup)
+        src = soup.attrs.get("src", "")
+        if src:
+            soup.attrs["src"] = to_pandoc_local_url(src)
+        return soup
     def dump_markdwon(self):
         alt = self._soup.attrs.get("alt", "")
         src = self._soup.attrs.get("src", "")
@@ -23,9 +28,17 @@ class ImgNode(BaseNode):
         if not src:
             return ""
 
+        src_out = to_pandoc_local_url(src)
+        src_out = f"<{src_out}>" if (" " in src_out or "\\" in src_out) else src_out
         if title:
-            return f'![{alt}]({src} "{title}")'
-        return f'![{alt}]({src})'
+            return f'![{alt}]({src_out} "{title}")'
+        return f'![{alt}]({src_out})'
+
+    def dump_docx_buffer(self):
+        text = self.dump_markdwon()
+        if not text:
+            return []
+        return [{'type': 'markdwonText', 'text': text}]