wuxinbo-bo/math-model-skills/delivery-assurance

 
if ! which xelatex 2>/dev/null; then
 
    echo "xelatex not found, attempting install..."
 
    if which miktex 2>/dev/null; then
 
        miktex packages install xetex ctex xecjk gbt7714 fontspec
 
        miktex fndb refresh
 
    elif which initexmf 2>/dev/null; then
 
        initexmf --set-config-value=[MPM]AutoInstall=1
 
    fi
 
fi
 
which xelatex && which bibtex && echo "ready" || echo "xelatex/bibtex not found"
 
fc-list :lang=zh | head -5
 
kpsewhich gbt7714.sty 2>/dev/null || echo "gbt7714.sty not found (will auto-install on first compile)"
 

 
if [ -f "工具/compile_utils.sh" ]; then
 
    bash 工具/compile_utils.sh 论文/
 
elif [ -f "skills/shared-scripts/compile_utils.sh" ]; then
 
    bash skills/shared-scripts/compile_utils.sh 论文/
 
else
 
    echo "compile_utils.sh not found, manual cleanup needed"
 
fi
 

 
# 检测并修复 tabular/longtable 中的单 \ 行结束符（应该是 \\）
 
# 这是 heredoc 不加引号导致 \\ 被转义为 \ 的常见问题
 
for f in 论文/章节/*.tex; do
 
    [ -f "$f" ] || continue
 
    # 检测：tabular 环境内，行末只有单个 \ 后跟换行（应该是 \\）
 
    if grep -P '(?<!\\)\\(?!\\)(?=\s*$)' "$f" | grep -v '\\begin\|\\end\|\\hline\|\\toprule\|\\midrule\|\\bottomrule\|\\caption\|\\label\|\\centering\|\\input\|\\include\|\\usepackage\|\\section\|\\subsection' > /dev/null 2>&1; then
 
        echo "⚠ $(basename $f): 可能有表格行结束符问题（单 \\ 应为 \\\\）"
 
        # 在 tabular/longtable 环境内，把行末的单 \ 替换为 \\
 
        python3 -c "
 
import re
 
with open('$f', 'r', encoding='utf-8') as fh:
 
    content = fh.read()
 
# 只在 tabular/longtable 环境内修复
 
def fix_table_endings(match):
 
    table = match.group(0)
 
    # 把数据行末尾的单 \ (后跟换行) 替换为 \\\\
 
    fixed = re.sub(r'(?<=&[^&\n]*)\\\s*\n', r'\\\\\\\\\n', table)
 
    return fixed
 
for env in ['tabular', 'longtable']:
 
    pattern = r'(\\\\begin\{' + env + r'[*]?\}.*?\\\\end\{' + env + r'[*]?\})'
 
    content = re.sub(pattern, fix_table_endings, content, flags=re.DOTALL)
 
with open('$f', 'w', encoding='utf-8') as fh:
 
    fh.write(content)
 
" 2>/dev/null
 
    fi
 
done
 

 
mkdir -p 临时文件
 
grep -oh '\\ref{[^}]*}' 论文/章节/*.tex 论文/论文正文.tex 2>/dev/null | sort -u > 临时文件/_refs.txt
 
grep -oh '\\label{[^}]*}' 论文/章节/*.tex 论文/论文正文.tex 2>/dev/null | sort -u > 临时文件/_labels.txt
 
comm -23 <(sed 's/\\ref/\\label/g' 临时文件/_refs.txt) 临时文件/_labels.txt > 临时文件/_missing_labels.txt
 
cat 临时文件/_missing_labels.txt
 

 
# 把所有错误引号统一为全角引号
 
for f in 论文/章节/*.tex; do
 
    [ -f "$f" ] || continue
 
    python3 -c "
 
import re
 
content = open('$f', 'r', encoding='utf-8').read()
 
# 保护数学环境
 
placeholders = []
 
def stash(m):
 
    placeholders.append(m.group(0)); return f'\\x00M{len(placeholders)-1}\\x00'
 
content = re.sub(r'\\\$[^\\\$]*\\\$', stash, content)
 
content = re.sub(r'\\\\\\[.*?\\\\\\]', stash, content, flags=re.DOTALL)
 
# 保护 \begin{verbatim}/lstlisting 等代码环境
 
content = re.sub(r'\\\\begin\{(verbatim|lstlisting|minted)\}.*?\\\\end\{\\1\}', stash, content, flags=re.DOTALL)
 
# 1. LaTeX 风格 ``...'' → 全角双引号
 
content = re.sub(r\"\`\`([^\`'\\\\n]+?)''\", '\u201c\\\\g<1>\u201d', content)
 
# 2. ASCII 直引号 \"...\" → 全角双引号（成对处理）
 
parts = content.split('\"')
 
if len(parts) > 2:
 
    result = parts[0]
 
    for i, p in enumerate(parts[1:], 1):
 
        result += ('\u201c' if i % 2 == 1 else '\u201d') + p
 
    content = result
 
# 还原
 
for i, ph in enumerate(placeholders):
 
    content = content.replace(f'\\x00M{i}\\x00', ph)
 
open('$f', 'w', encoding='utf-8').write(content)
 
" 2>/dev/null
 
done
 

 
UNEMBED=0
 
# Validate PDF visuals
 
for pdf in 图表/*.pdf; do
 
    [ -f "$pdf" ] || continue
 
    bn=$(basename "$pdf")
 
    python3 -c "import json,sys; d=json.load(open('图表/figure_manifest.json',encoding='utf-8')); sys.exit(0 if any(x.get('publish') and x.get('path','').replace('\\\\','/').endswith('/'+sys.argv[1]) for x in d.get('figures',[])) else 1)" "$bn" || continue
 
    grep -rq "$bn" 论文/章节/*.tex 论文/论文正文.tex 2>/dev/null || { echo "UNEMBEDDED PDF: $bn"; UNEMBED=$((UNEMBED+1)); }
 
done
 
# Validate only TABLE_*.tex files selected by the manuscript embedding plan
 
for tbl in 图表/TABLE_*.tex; do
 
    [ -f "$tbl" ] || continue
 
    bn=$(basename "$tbl")
 
    python3 -c "import json,sys; d=json.load(open('图表/figure_manifest.json',encoding='utf-8')); sys.exit(0 if any(x.get('publish') and x.get('path','').replace('\\\\','/').endswith('/'+sys.argv[1]) for x in d.get('tables',[])) else 1)" "$bn" || continue
 
    # Validate if any label from this table file appears in sections
 
    for lbl in $(grep -oh '\\label{[^}]*}' "$tbl" 2>/dev/null); do
 
        grep -rq "$lbl" 论文/章节/*.tex 论文/论文正文.tex 2>/dev/null || { echo "UNEMBEDDED TABLE: $lbl (from $bn)"; UNEMBED=$((UNEMBED+1)); }
 
    done
 
done
 
# Raw 图表引用.tex labels are diagnostic; the published asset loops above remain authoritative
 
echo "Total unembedded: $UNEMBED"
 

 
# Diagnose generated PDFs; only publish=true omissions are blocking
 
for pdf in 图表/*.pdf; do
 
    [ -f "$pdf" ] || continue
 
    bn=$(basename "$pdf")
 
    python3 -c "import json,sys; d=json.load(open('图表/figure_manifest.json',encoding='utf-8')); sys.exit(0 if any(x.get('publish') and x.get('path','').replace('\\\\','/').endswith('/'+sys.argv[1]) for x in d.get('figures',[])) else 1)" "$bn" || continue
 
    grep -rq "$bn" 论文/章节/*.tex 论文/论文正文.tex 2>/dev/null || echo "⚠ $bn not referenced"
 
done
 

 
cd 论文/
 
xelatex -interaction=nonstopmode 论文正文.tex
 
bibtex 论文正文
 
xelatex -interaction=nonstopmode 论文正文.tex
 
xelatex -interaction=nonstopmode 论文正文.tex
 

 
# Count critical errors
 
MATH_ERR=$(grep -c 'Bad math environment delimiter\|Missing \$ inserted\|begin{document} ended by' 论文/编译日志.log 2>/dev/null || echo 0)
 
LR_ERR=$(grep -c 'Not allowed in LR mode' 论文/编译日志.log 2>/dev/null || echo 0)
 
UNDEF_CS=$(grep -c 'Undefined control sequence' 论文/编译日志.log 2>/dev/null || echo 0)
 
TOTAL_ERR=$((MATH_ERR + LR_ERR))
 
echo "Math errors: $MATH_ERR, LR mode errors: $LR_ERR, Undefined CS: $UNDEF_CS"
 
if [ "$TOTAL_ERR" -gt 0 ]; then
 
    echo "CRITICAL: $TOTAL_ERR errors — MUST FIX prior to proceeding"
 
    # Show error locations
 
    grep -B2 'Bad math\|Missing \$ inserted\|begin{document} ended\|Not allowed in LR mode' 论文/编译日志.log | grep -E '^\./|^l\.' | head -20
 
fi
 

 
cd 论文/
 
xelatex -interaction=nonstopmode 论文正文.tex
 
bibtex 论文正文 2>&1 | tail -5
 
xelatex -interaction=nonstopmode 论文正文.tex