Zhengshou Lai
75bb7dec32
- Move docx post-processing from convert.py to template-specific postprocess.py hooks - Resolve relative markdown image paths before pandoc for docx and pdf - Auto-generate centered figure captions (图 1, 图 2...) in docx - Center tables and apply three-line table borders in docx - Left-align tables in PDF via template.typ show rule
405 lines
18 KiB
Python
405 lines
18 KiB
Python
"""Default post-processing for md→docx conversion.
|
|
|
|
This script is loaded dynamically by mytoolkit.convert after pandoc has
|
|
produced the docx. The entry point is ``postprocess(docx_path, reference_doc_path)``.
|
|
"""
|
|
|
|
from pathlib import Path
|
|
|
|
|
|
def postprocess(docx_path: Path, reference_doc_path: str | None = None) -> None:
|
|
"""Post-process pandoc-generated docx for Chinese academic typography.
|
|
|
|
Applies the following fixes:
|
|
- Center image paragraphs and auto-generate captions (图 1, 图 2, ...)
|
|
- Inject Caption style into styles.xml
|
|
- Apply paragraph-level typography from reference-doc Normal style
|
|
(first-line indent, spacing, line spacing, justification)
|
|
- Convert BodyText paragraphs to Normal and apply same typography
|
|
- Add heading spacing before/after Heading 1-4
|
|
- Add 6pt spacing after reference entries (detected after "参考文献")
|
|
- Three-line table borders (1.5pt top/bottom, 0.75pt header separator)
|
|
- Center tables on the page
|
|
- Remove table styles that override custom borders
|
|
- Remove first-line indent inside table cells
|
|
- Add 6pt spacing before paragraphs following tables
|
|
- Convert '---' horizontal rules to HorizontalRule style (no indent)
|
|
- Remove first-line indent from empty paragraphs
|
|
- Inject HorizontalRule style into styles.xml
|
|
"""
|
|
try:
|
|
import lxml.etree as ET
|
|
except ImportError:
|
|
return
|
|
|
|
import zipfile
|
|
import os
|
|
import copy
|
|
from tempfile import TemporaryDirectory
|
|
|
|
W = "http://schemas.openxmlformats.org/wordprocessingml/2006/main"
|
|
wtag = lambda t: "{" + W + "}" + t
|
|
|
|
def _paragraph_text(p):
|
|
parts = []
|
|
for r in p.findall(wtag("r")):
|
|
t = r.find(wtag("t"))
|
|
if t is not None and t.text:
|
|
parts.append(t.text)
|
|
return "".join(parts)
|
|
|
|
def _copy_ppr_children(src_ppr, dst_ppr):
|
|
for child in src_ppr:
|
|
tag_name = child.tag.split("}")[-1]
|
|
# Remove existing same-tag elements
|
|
for existing in list(dst_ppr.findall(wtag(tag_name))):
|
|
dst_ppr.remove(existing)
|
|
dst_ppr.append(copy.deepcopy(child))
|
|
|
|
with TemporaryDirectory() as workdir:
|
|
with zipfile.ZipFile(docx_path, "r") as z:
|
|
z.extractall(workdir)
|
|
|
|
# --- Load reference-doc Normal style paragraph properties ---
|
|
normal_ppr = None
|
|
if reference_doc_path and Path(reference_doc_path).exists():
|
|
try:
|
|
with zipfile.ZipFile(reference_doc_path, "r") as z:
|
|
styles_content = z.read("word/styles.xml")
|
|
ref_styles_root = ET.fromstring(styles_content)
|
|
for style in ref_styles_root.findall(wtag("style")):
|
|
if style.get(wtag("styleId")) == "Normal":
|
|
normal_ppr = style.find(wtag("pPr"))
|
|
break
|
|
except Exception:
|
|
normal_ppr = None
|
|
|
|
# Heading spacing in twips (1pt = 20 twips)
|
|
heading_spacing = {
|
|
"Heading1": {"before": "360", "after": "120"},
|
|
"Heading2": {"before": "280", "after": "120"},
|
|
"Heading3": {"before": "200", "after": "80"},
|
|
"Heading4": {"before": "160", "after": "80"},
|
|
}
|
|
|
|
doc_xml = os.path.join(workdir, "word", "document.xml")
|
|
tree = ET.parse(doc_xml)
|
|
root = tree.getroot()
|
|
body = root.find(".//" + wtag("body"))
|
|
if body is None:
|
|
return
|
|
|
|
# --- 1. Table borders (three-line) + centering ---
|
|
for tbl in body.findall(".//" + wtag("tbl")):
|
|
tblPr = tbl.find(wtag("tblPr"))
|
|
if tblPr is None:
|
|
tblPr = ET.SubElement(tbl, wtag("tblPr"))
|
|
tbl.insert(0, tblPr)
|
|
# Remove table style so borders are not overridden
|
|
for ts in list(tblPr.findall(wtag("tblStyle"))):
|
|
tblPr.remove(ts)
|
|
# Center the table on the page.
|
|
for existing in list(tblPr.findall(wtag("jc"))):
|
|
tblPr.remove(existing)
|
|
jc = ET.SubElement(tblPr, wtag("jc"))
|
|
jc.set(wtag("val"), "center")
|
|
for existing in list(tblPr.findall(wtag("tblBorders"))):
|
|
tblPr.remove(existing)
|
|
borders = ET.SubElement(tblPr, wtag("tblBorders"))
|
|
for pos, sz in [("top", "12"), ("bottom", "12")]:
|
|
b = ET.SubElement(borders, wtag(pos))
|
|
b.set(wtag("val"), "single")
|
|
b.set(wtag("sz"), sz)
|
|
b.set(wtag("space"), "0")
|
|
b.set(wtag("color"), "auto")
|
|
for pos in ["left", "right", "insideH", "insideV"]:
|
|
b = ET.SubElement(borders, wtag(pos))
|
|
b.set(wtag("val"), "none")
|
|
b.set(wtag("sz"), "0")
|
|
b.set(wtag("space"), "0")
|
|
b.set(wtag("color"), "auto")
|
|
# Header row bottom border
|
|
rows = tbl.findall(wtag("tr"))
|
|
if rows:
|
|
for tc in rows[0].findall(wtag("tc")):
|
|
tcPr = tc.find(wtag("tcPr"))
|
|
if tcPr is None:
|
|
tcPr = ET.SubElement(tc, wtag("tcPr"))
|
|
for existing in list(tcPr.findall(wtag("tcBorders"))):
|
|
tcPr.remove(existing)
|
|
tcBorders = ET.SubElement(tcPr, wtag("tcBorders"))
|
|
for pos in ["top", "left", "right"]:
|
|
b = ET.SubElement(tcBorders, wtag(pos))
|
|
b.set(wtag("val"), "none")
|
|
b.set(wtag("sz"), "0")
|
|
b.set(wtag("space"), "0")
|
|
b.set(wtag("color"), "auto")
|
|
bottom = ET.SubElement(tcBorders, wtag("bottom"))
|
|
bottom.set(wtag("val"), "single")
|
|
bottom.set(wtag("sz"), "6")
|
|
bottom.set(wtag("space"), "0")
|
|
bottom.set(wtag("color"), "auto")
|
|
|
|
# --- 2. Image captions and centering ---
|
|
def _set_paragraph_alignment(p, align):
|
|
pPr = p.find(wtag("pPr"))
|
|
if pPr is None:
|
|
pPr = ET.SubElement(p, wtag("pPr"))
|
|
p.insert(0, pPr)
|
|
for jc in list(pPr.findall(wtag("jc"))):
|
|
pPr.remove(jc)
|
|
jc = ET.SubElement(pPr, wtag("jc"))
|
|
jc.set(wtag("val"), align)
|
|
|
|
def _has_drawing(p):
|
|
return p.find(".//" + wtag("drawing")) is not None
|
|
|
|
drawing_ns = "http://schemas.openxmlformats.org/drawingml/2006/main"
|
|
image_count = 0
|
|
# Iterate over a snapshot because we insert caption paragraphs and may remove ImageCaption.
|
|
for p in list(body.findall(wtag("p"))):
|
|
if not _has_drawing(p):
|
|
continue
|
|
# Center the image paragraph.
|
|
_set_paragraph_alignment(p, "center")
|
|
image_count += 1
|
|
|
|
# Gather alt text: prefer pandoc-generated ImageCaption, fallback to drawing docPr.
|
|
alt = ""
|
|
p_idx = list(body).index(p)
|
|
next_p = body[p_idx + 1] if p_idx + 1 < len(list(body)) else None
|
|
if next_p is not None and next_p.tag == wtag("p"):
|
|
next_style = next_p.find(".//" + wtag("pStyle"))
|
|
if next_style is not None and next_style.get(wtag("val")) == "ImageCaption":
|
|
parts = []
|
|
for r in next_p.findall(wtag("r")):
|
|
t = r.find(wtag("t"))
|
|
if t is not None and t.text:
|
|
parts.append(t.text)
|
|
if parts:
|
|
alt = "".join(parts).strip()
|
|
body.remove(next_p)
|
|
|
|
if not alt:
|
|
drawing = p.find(".//" + wtag("drawing"))
|
|
if drawing is not None:
|
|
docPr = drawing.find(f".//{{{drawing_ns}}}docPr")
|
|
if docPr is not None:
|
|
alt = docPr.get("descr", "").strip()
|
|
|
|
caption_text = f"图 {image_count}"
|
|
if alt:
|
|
caption_text = f"图 {image_count} {alt}"
|
|
|
|
# Insert caption paragraph after the image paragraph.
|
|
caption_p = ET.Element(wtag("p"))
|
|
caption_pPr = ET.SubElement(caption_p, wtag("pPr"))
|
|
ET.SubElement(caption_pPr, wtag("pStyle")).set(wtag("val"), "Caption")
|
|
_set_paragraph_alignment(caption_p, "center")
|
|
ET.SubElement(caption_pPr, wtag("ind")).set(wtag("firstLine"), "0")
|
|
spacing = ET.SubElement(caption_pPr, wtag("spacing"))
|
|
spacing.set(wtag("before"), "60")
|
|
spacing.set(wtag("after"), "120")
|
|
r = ET.SubElement(caption_p, wtag("r"))
|
|
rPr = ET.SubElement(r, wtag("rPr"))
|
|
ET.SubElement(rPr, wtag("sz")).set(wtag("val"), "22")
|
|
ET.SubElement(rPr, wtag("szCs")).set(wtag("val"), "22")
|
|
t = ET.SubElement(r, wtag("t"))
|
|
t.text = caption_text
|
|
# Recompute index because we may have removed the next paragraph.
|
|
p_idx = list(body).index(p)
|
|
body.insert(p_idx + 1, caption_p)
|
|
|
|
# --- 3. Remove indent in table cells ---
|
|
for tc in body.findall(".//" + wtag("tc")):
|
|
for p in tc.findall(wtag("p")):
|
|
pPr = p.find(wtag("pPr"))
|
|
if pPr is None:
|
|
pPr = ET.SubElement(p, wtag("pPr"))
|
|
for ind in list(pPr.findall(wtag("ind"))):
|
|
pPr.remove(ind)
|
|
ET.SubElement(pPr, wtag("ind")).set(wtag("firstLine"), "0")
|
|
spacing = pPr.find(wtag("spacing"))
|
|
if spacing is not None:
|
|
spacing.set(wtag("before"), "0")
|
|
|
|
# --- 4. Horizontal rule + empty paragraphs ---
|
|
for p in body.findall(wtag("p")):
|
|
p_str = ET.tostring(p, encoding="unicode")
|
|
is_hr = "o:hr=" in p_str and "o:hrstd=" in p_str
|
|
has_text = False
|
|
for r in p.findall(wtag("r")):
|
|
t = r.find(wtag("t"))
|
|
if t is not None and t.text and t.text.strip():
|
|
has_text = True
|
|
break
|
|
if is_hr:
|
|
pPr = p.find(wtag("pPr"))
|
|
if pPr is None:
|
|
pPr = ET.SubElement(p, wtag("pPr"))
|
|
p.insert(0, pPr)
|
|
for ps in list(pPr.findall(wtag("pStyle"))):
|
|
pPr.remove(ps)
|
|
ET.SubElement(pPr, wtag("pStyle")).set(wtag("val"), "HorizontalRule")
|
|
for ind in list(pPr.findall(wtag("ind"))):
|
|
pPr.remove(ind)
|
|
ET.SubElement(pPr, wtag("ind")).set(wtag("firstLine"), "0")
|
|
spacing = pPr.find(wtag("spacing"))
|
|
if spacing is not None:
|
|
spacing.set(wtag("before"), "0")
|
|
elif not has_text:
|
|
pPr = p.find(wtag("pPr"))
|
|
if pPr is None:
|
|
pPr = ET.SubElement(p, wtag("pPr"))
|
|
for ind in list(pPr.findall(wtag("ind"))):
|
|
pPr.remove(ind)
|
|
ET.SubElement(pPr, wtag("ind")).set(wtag("firstLine"), "0")
|
|
spacing = pPr.find(wtag("spacing"))
|
|
if spacing is not None:
|
|
spacing.set(wtag("before"), "0")
|
|
|
|
# --- 5. Apply paragraph-level typography from reference doc ---
|
|
in_references = False
|
|
for p in body.findall(wtag("p")):
|
|
# Skip paragraphs inside table cells (handled separately)
|
|
parent = p.getparent()
|
|
if parent is not None and parent.tag == wtag("tc"):
|
|
continue
|
|
|
|
pPr = p.find(wtag("pPr"))
|
|
if pPr is None:
|
|
pPr = ET.SubElement(p, wtag("pPr"))
|
|
p.insert(0, pPr)
|
|
|
|
pStyle = pPr.find(wtag("pStyle"))
|
|
style_id = pStyle.get(wtag("val")) if pStyle is not None else "Normal"
|
|
|
|
# Detect references section by heading text
|
|
if style_id.startswith("Heading") and "参考文献" in _paragraph_text(p):
|
|
in_references = True
|
|
# Apply heading spacing
|
|
hs = heading_spacing.get(style_id)
|
|
if hs is not None:
|
|
spacing = pPr.find(wtag("spacing"))
|
|
if spacing is None:
|
|
spacing = ET.SubElement(pPr, wtag("spacing"))
|
|
spacing.set(wtag("before"), hs["before"])
|
|
spacing.set(wtag("after"), hs["after"])
|
|
continue
|
|
|
|
# Reference entry formatting
|
|
if in_references:
|
|
text = _paragraph_text(p).strip()
|
|
if not text:
|
|
# Empty paragraph in refs: remove indent but keep normal spacing
|
|
for ind in list(pPr.findall(wtag("ind"))):
|
|
pPr.remove(ind)
|
|
ET.SubElement(pPr, wtag("ind")).set(wtag("firstLine"), "0")
|
|
continue
|
|
# Convert to Normal and apply normal pPr
|
|
if pStyle is None:
|
|
pStyle = ET.SubElement(pPr, wtag("pStyle"))
|
|
pStyle.set(wtag("val"), "Normal")
|
|
if normal_ppr is not None:
|
|
_copy_ppr_children(normal_ppr, pPr)
|
|
spacing = pPr.find(wtag("spacing"))
|
|
if spacing is None:
|
|
spacing = ET.SubElement(pPr, wtag("spacing"))
|
|
spacing.set(wtag("after"), "120") # 6pt after each reference
|
|
continue
|
|
|
|
# BodyText / FirstParagraph -> Normal
|
|
if style_id in ("BodyText", "FirstParagraph"):
|
|
if pStyle is None:
|
|
pStyle = ET.SubElement(pPr, wtag("pStyle"))
|
|
pStyle.set(wtag("val"), "Normal")
|
|
style_id = "Normal"
|
|
|
|
# Apply Normal paragraph properties from reference doc
|
|
if style_id in ("Normal", "FirstParagraph") and normal_ppr is not None:
|
|
_copy_ppr_children(normal_ppr, pPr)
|
|
|
|
# Apply heading spacing
|
|
if style_id in heading_spacing:
|
|
spacing = pPr.find(wtag("spacing"))
|
|
if spacing is None:
|
|
spacing = ET.SubElement(pPr, wtag("spacing"))
|
|
spacing.set(wtag("before"), heading_spacing[style_id]["before"])
|
|
spacing.set(wtag("after"), heading_spacing[style_id]["after"])
|
|
|
|
# --- 6. Add spacing after tables ---
|
|
for tbl in body.findall(wtag("tbl")):
|
|
tbl_idx = list(body).index(tbl)
|
|
for i in range(tbl_idx + 1, len(list(body))):
|
|
next_el = list(body)[i]
|
|
if next_el.tag == wtag("p"):
|
|
pPr = next_el.find(wtag("pPr"))
|
|
if pPr is None:
|
|
pPr = ET.SubElement(next_el, wtag("pPr"))
|
|
spacing = pPr.find(wtag("spacing"))
|
|
if spacing is None:
|
|
spacing = ET.SubElement(pPr, wtag("spacing"))
|
|
spacing.set(wtag("before"), "120")
|
|
break
|
|
|
|
# --- 7. Inject suppressAutoHyphens into all paragraphs ---
|
|
for p in body.findall(wtag("p")):
|
|
pPr = p.find(wtag("pPr"))
|
|
if pPr is None:
|
|
pPr = ET.SubElement(p, wtag("pPr"))
|
|
p.insert(0, pPr)
|
|
if pPr.find(wtag("suppressAutoHyphens")) is None:
|
|
ET.SubElement(pPr, wtag("suppressAutoHyphens"))
|
|
|
|
tree.write(doc_xml, xml_declaration=True, encoding="UTF-8", pretty_print=False)
|
|
|
|
# --- 8. Inject HorizontalRule and Caption styles ---
|
|
styles_xml = os.path.join(workdir, "word", "styles.xml")
|
|
styles_tree = ET.parse(styles_xml)
|
|
styles_root = styles_tree.getroot()
|
|
normal_style = None
|
|
for style in styles_root.findall(wtag("style")):
|
|
if style.get(wtag("styleId")) == "Normal":
|
|
normal_style = style
|
|
break
|
|
if normal_style is not None:
|
|
# Remove existing custom styles to avoid duplicates.
|
|
for style in list(styles_root.findall(wtag("style"))):
|
|
if style.get(wtag("styleId")) in ("HorizontalRule", "Caption"):
|
|
styles_root.remove(style)
|
|
|
|
# HorizontalRule style
|
|
hr_style = ET.Element(wtag("style"))
|
|
hr_style.set(wtag("type"), "paragraph")
|
|
hr_style.set(wtag("styleId"), "HorizontalRule")
|
|
ET.SubElement(hr_style, wtag("name")).set(wtag("val"), "Horizontal Rule")
|
|
ET.SubElement(hr_style, wtag("basedOn")).set(wtag("val"), "Normal")
|
|
pPr = ET.SubElement(hr_style, wtag("pPr"))
|
|
ET.SubElement(pPr, wtag("ind")).set(wtag("firstLine"), "0")
|
|
|
|
# Caption style: centered, 11pt, no first-line indent
|
|
caption_style = ET.Element(wtag("style"))
|
|
caption_style.set(wtag("type"), "paragraph")
|
|
caption_style.set(wtag("styleId"), "Caption")
|
|
ET.SubElement(caption_style, wtag("name")).set(wtag("val"), "Caption")
|
|
ET.SubElement(caption_style, wtag("basedOn")).set(wtag("val"), "Normal")
|
|
ET.SubElement(caption_style, wtag("qFormat"))
|
|
cap_pPr = ET.SubElement(caption_style, wtag("pPr"))
|
|
ET.SubElement(cap_pPr, wtag("jc")).set(wtag("val"), "center")
|
|
ET.SubElement(cap_pPr, wtag("ind")).set(wtag("firstLine"), "0")
|
|
ET.SubElement(cap_pPr, wtag("spacing")).set(wtag("after"), "120")
|
|
cap_rPr = ET.SubElement(caption_style, wtag("rPr"))
|
|
ET.SubElement(cap_rPr, wtag("sz")).set(wtag("val"), "22")
|
|
ET.SubElement(cap_rPr, wtag("szCs")).set(wtag("val"), "22")
|
|
|
|
idx = list(styles_root).index(normal_style)
|
|
styles_root.insert(idx + 1, hr_style)
|
|
styles_root.insert(idx + 2, caption_style)
|
|
styles_tree.write(styles_xml, xml_declaration=True, encoding="UTF-8", pretty_print=False)
|
|
|
|
with zipfile.ZipFile(docx_path, "w", zipfile.ZIP_DEFLATED) as zout:
|
|
for rd, _, files in os.walk(workdir):
|
|
for file in files:
|
|
fp = os.path.join(rd, file)
|
|
zout.write(fp, os.path.relpath(fp, workdir))
|