Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-09 03:04:10 -04:00
Code Issues Packages Projects Releases Wiki Activity

Add a contains text selector

Browse Source
This commit is contained in:
Kovid Goyal 2021-11-11 10:43:21 +05:30
parent b50834b23d
commit 9f2c6a9ab6
No known key found for this signature in database
GPG Key ID: 06BC317B515ACE7C
1 changed files with 27 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

29
src/calibre/ebooks/html_transform_rules.py
View File

@ -3,6 +3,7 @@
# License: GPLv3 Copyright: 2016, Kovid Goyal <kovid at kovidgoyal.net> # License: GPLv3 Copyright: 2016, Kovid Goyal <kovid at kovidgoyal.net>
import re
from functools import partial from functools import partial
from html5_parser import parse from html5_parser import parse
from lxml import etree from lxml import etree
@ -102,6 +103,7 @@ MATCH_TYPE_MAP = {m.name: m for m in (
Match('css', _('matches CSS selector'), _('CSS selector'), validate_css_selector), Match('css', _('matches CSS selector'), _('CSS selector'), validate_css_selector),
Match('xpath', _('matches XPath selector'), _('XPath selector'), validate_xpath_selector), Match('xpath', _('matches XPath selector'), _('XPath selector'), validate_xpath_selector),
Match('*', _('is any tag')), Match('*', _('is any tag')),
Match('contains_text', _('contains text'), _('Text')),
)} )}
allowed_keys = frozenset('match_type query actions'.split()) allowed_keys = frozenset('match_type query actions'.split())
@ -338,6 +340,24 @@ def create_action(serialized_action):
return action_map[serialized_action['type']](serialized_action.get('data', '')) return action_map[serialized_action['type']](serialized_action.get('data', ''))
def text_as_xpath_literal(text):
if '"' in text:
if "'" not in text:
return f"'{text}'"
parts = []
for x in re.split(r'(")', text):
if not x:
continue
if x == '"':
x = "'\"'"
else:
x = f'"{x}"'
parts.append(x)
return f'concat({",".join(parts)})'
return f'"{text}"'
class Rule: class Rule:
def __init__(self, serialized_rule): def __init__(self, serialized_rule):
@ -359,6 +379,9 @@ class Rule:
elif mt == 'not_has_class': elif mt == 'not_has_class':
self.css_selector = f":not(.{q})" self.css_selector = f":not(.{q})"
self.selector = self.css self.selector = self.css
elif mt == 'contains_text':
self.xpath_selector = XPath(f'//*[contains(text(), {text_as_xpath_literal(q)})]')
self.selector = self.xpath
else: else:
raise KeyError(f'Unknown match_type: {mt}') raise KeyError(f'Unknown match_type: {mt}')
self.actions = tuple(map(create_action, serialized_rule['actions'])) self.actions = tuple(map(create_action, serialized_rule['actions']))
@ -476,8 +499,8 @@ def test(return_tests=False): # {{{
<html id='root'> <html id='root'>
<head id='head'></head> <head id='head'></head>
<body id='body'> <body id='body'>
<p class="one red" id='p1'> <p class="one red" id='p1'>simple
<p class="two green" id='p2'> <p class="two green" id='p2'>a'b"c
''') ''')
all_ids = root.xpath('//*/@id') all_ids = root.xpath('//*/@id')
@ -500,6 +523,8 @@ def test(return_tests=False): # {{{
t('not_has_class', 'one', ei) t('not_has_class', 'one', ei)
t('css', '#body > p.red', ['p1']) t('css', '#body > p.red', ['p1'])
t('xpath', '//h:body', ['body']) t('xpath', '//h:body', ['body'])
t('contains_text', 'imple', ['p1'])
t('contains_text', 'a\'b"c', ['p2'])
def test_validate_rule(self): def test_validate_rule(self):
def av(match_type='*', query='', atype='remove', adata=''): def av(match_type='*', query='', atype='remove', adata=''):