modm_data.html.parser

  1# Copyright 2022, Niklas Hauser
  2# SPDX-License-Identifier: MPL-2.0
  3
  4import re
  5import os.path
  6import logging
  7from functools import cached_property
  8from html.parser import HTMLParser
  9from .table import Table, Cell
 10from .text import Text, Heading
 11
 12LOGGER = logging.getLogger(__name__)
 13
 14class Parser(HTMLParser):
 15    def __init__(self):
 16        super().__init__(convert_charrefs=True)
 17        self._items = []
 18        self._ignore_tags = ["span"]
 19        self._type = None
 20        self._tags = []
 21
 22        self._ty = -1
 23        self._tx = -1
 24        self._table = None
 25        self._cell = None
 26        self._data = ""
 27        self._collect_data = False
 28
 29    def _clear_data(self):
 30        self._collect_data = False
 31        data = self._data.replace("\n", "").replace("\r", "")
 32        data = data.strip()
 33        return data
 34
 35    def handle_starttag(self, tag, attrs):
 36        if self._collect_data and tag not in self._ignore_tags:
 37            self._data += f"<{tag}>"
 38
 39        if tag in ["table", "th", "tr", "td", "caption"]:
 40            self._data = ""
 41            self._collect_data = True
 42            if tag == "table":
 43                heading = next((i for i in reversed(self._items) if isinstance(i, Heading)), None)
 44                self._table = Table(heading=heading)
 45                self._type = "t"
 46                self._ty = -1
 47            if self._table and tag == "tr":
 48                self._ty += 1
 49                self._tx = -1
 50            if self._table and tag in ["th", "td"]:
 51                self._tx += 1
 52                tys = next((a[1] for a in  attrs if a[0] == "rowspan"), 1)
 53                txs = next((a[1] for a in  attrs if a[0] == "colspan"), 1)
 54                self._cell = Cell(self._tx, self._ty, int(txs), int(tys), tag == "th")
 55
 56        elif re.match(r"h[1-6]", tag):
 57            self._data = ""
 58            self._collect_data = True
 59            self._type = "h"
 60
 61        elif self._type is None:
 62            self._data = ""
 63            self._collect_data = True
 64            self._type = (tag, len(self._tags))
 65
 66        self._tags.append(tag)
 67
 68    def handle_data(self, data):
 69        if self._collect_data:
 70            self._data += data
 71
 72    def handle_endtag(self, tag):
 73        self._tags.pop()
 74
 75        if re.match(r"h[1-6]", tag):
 76            self._items.append(Heading(self._clear_data()))
 77            self._type = None
 78
 79        elif self._table and tag == "caption":
 80            self._table._caption = Text(self._clear_data())
 81
 82        elif self._cell and tag in ["th", "td"]:
 83            self._cell.html = self._clear_data()
 84            self._table._cells.append(self._cell)
 85            self._cell = None
 86
 87        elif self._table and tag == "table":
 88            if self._table._cells:
 89                self._table._normalize()
 90                if self._table.size > (1,1) or self._table.cell(0,0).html != "(omitted)":
 91                    self._items.append(self._table)
 92            self._table = None
 93            self._type = None
 94
 95        if self._type == (tag, len(self._tags)):
 96            self._type = None
 97            self._items.append(Text(self._clear_data()))
 98
 99        if self._collect_data and tag not in self._ignore_tags:
100            self._data += f"</{tag}>"