# -*- coding: utf-8 -*-
"""Extract text + tables from all docx files in this folder to .txt files."""
import os
from docx import Document

BASE = os.path.dirname(os.path.abspath(__file__))

def iter_block_items(doc):
    from docx.oxml.ns import qn
    body = doc.element.body
    for child in body.iterchildren():
        if child.tag == qn('w:p'):
            yield ('p', child)
        elif child.tag == qn('w:tbl'):
            yield ('tbl', child)

def extract(path):
    doc = Document(path)
    out = []
    for kind, el in iter_block_items(doc):
        if kind == 'p':
            from docx.text.paragraph import Paragraph
            p = Paragraph(el, doc)
            t = p.text.strip()
            if t:
                style = p.style.name if p.style else ''
                prefix = '#' * 0
                if style.startswith('Heading'):
                    try:
                        lvl = int(style.split()[-1])
                        prefix = '#' * lvl + ' '
                    except Exception:
                        prefix = '# '
                out.append(prefix + t)
        else:
            from docx.table import Table
            tbl = Table(el, doc)
            out.append('[TABLE]')
            for row in tbl.rows:
                cells = [c.text.strip().replace('\n', ' / ') for c in row.cells]
                # dedupe merged cells
                dedup = []
                prev = None
                for c in cells:
                    dedup.append(c)
                out.append(' | '.join(dedup))
            out.append('[/TABLE]')
    return '\n'.join(out)

for fn in os.listdir(BASE):
    if fn.lower().endswith('.docx'):
        src = os.path.join(BASE, fn)
        dst = os.path.join(BASE, fn + '.txt')
        try:
            text = extract(src)
            with open(dst, 'w', encoding='utf-8') as f:
                f.write(text)
            print(f'{fn}: {len(text)} chars')
        except Exception as e:
            print(f'{fn}: ERROR {e}')