| |
| |
|
|
| """Strict rich_tabular_v3 reverse reader. Other LaTeX uses the legacy parser.""" |
| import html,re |
|
|
| TAGS={'textstrong':'b','textem':'i','textbf':'b','textit':'i','underline':'u','sout':'s', |
| 'textsuperscript':'sup','textsubscript':'sub'} |
|
|
| LITERALS={'textbackslash':'\\','textasciitilde':'~','textasciicircum':'^', |
| 'textless':'<','textgreater':'>'} |
|
|
| def split_top(text,delimiter): |
| parts=[];start=0;depth=0;i=0 |
| while i<len(text): |
| if depth==0 and text.startswith(delimiter,i): |
| parts.append(text[start:i]);i+=len(delimiter);start=i;continue |
| if text[i]=='\\': |
| i+=2;continue |
| if text[i]=='{':depth+=1 |
| elif text[i]=='}':depth-=1 |
| if depth<0:raise ValueError('unbalanced_generated_latex') |
| i+=1 |
| if depth:raise ValueError('unbalanced_generated_latex') |
| parts.append(text[start:]);return parts |
|
|
| def argument(text,pos): |
| if pos>=len(text) or text[pos]!='{':raise ValueError('expected_braced_argument') |
| start=pos+1;depth=1;pos+=1 |
| while pos<len(text): |
| if text[pos]=='\\':pos+=2;continue |
| if text[pos]=='{':depth+=1 |
| elif text[pos]=='}': |
| depth-=1 |
| if depth==0:return text[start:pos],pos+1 |
| pos+=1 |
| raise ValueError('unbalanced_generated_latex') |
|
|
| def inline_html(text): |
| try: |
| from .hybrid_inline import inline_html as decode |
| except ImportError: |
| from hybrid_inline import inline_html as decode |
| return decode(text) |
|
|
| def cell_parts(text): |
| text=text.strip();rs=cs=1 |
| while text.startswith((r'\multicolumn',r'\multirow')): |
| command='multicolumn' if text.startswith(r'\multicolumn') else 'multirow';pos=len(command)+1 |
| count,pos=argument(text,pos);_,pos=argument(text,pos);body,pos=argument(text,pos) |
| if text[pos:].strip():raise ValueError('trailing_span_content') |
| if command=='multicolumn':cs=int(count) |
| else:rs=int(count) |
| text=body |
| header=False |
| if text.startswith(r'\thead{'): |
| body,end=argument(text,len(r'\thead')) |
| if text[end:].strip():raise ValueError('trailing_header_content') |
| text=body |
| header=True |
| return rs,cs,inline_html(text),header |
|
|
| def to_html(latex): |
| m=re.fullmatch(r'\\begin\{tabular\}\{[clrx]+\}\n(.*?)\n\\end\{tabular\}',latex,re.S) |
| if not m:raise ValueError('unsupported_generated_tabular') |
| rows=split_top(m.group(1),r'\\') |
| if rows[-1].strip():raise ValueError('missing_final_row_separator') |
| columns=len(re.match(r'\\begin\{tabular\}\{([clrx]+)\}',latex).group(1)) |
| rows.pop();occupied=set();out=['<table>'] |
| if not rows or len(rows)>4096 or columns>512:raise ValueError('generated_grid_size') |
| for r,row in enumerate(rows): |
| out.append('<tr>');c=0 |
| for part in split_top(row,'&'): |
| rs,cs,content,header=cell_parts(part) |
| if rs<1 or cs<1 or r+rs>len(rows) or c+cs>columns:raise ValueError('invalid_generated_span') |
| if (r,c) in occupied: |
| if content or header or rs!=1:raise ValueError('nonempty_span_placeholder') |
| if any((r,cc) not in occupied for cc in range(c,c+cs)):raise ValueError('invalid_span_placeholder') |
| c+=cs;continue |
| if any((rr,cc) in occupied for rr in range(r,r+rs) for cc in range(c,c+cs)): |
| raise ValueError('overlapping_generated_span') |
| tag='th' if header else 'td' |
| out.append('<'+tag+' rowspan="'+str(rs)+'" colspan="'+str(cs)+'">'+content+'</'+tag+'>') |
| for rr in range(r,r+rs): |
| for cc in range(c,c+cs):occupied.add((rr,cc)) |
| c+=cs |
| if c!=columns:raise ValueError('generated_column_count') |
| out.append('</tr>') |
| return ''.join(out)+'</table>' |
|
|
