Mercurial > genshi > genshi-test
comparison genshi/util.py @ 433:6d01e91f2a49
More API docs.
| author | cmlenz |
|---|---|
| date | Thu, 22 Mar 2007 21:12:03 +0000 |
| parents | 5b248708bbed |
| children | 4145dd84001e f0bb2c5ea0ff |
comparison
equal
deleted
inserted
replaced
| 432:3879c9ad3472 | 433:6d01e91f2a49 |
|---|---|
| 137 item.next = self.head | 137 item.next = self.head |
| 138 self.head.previous = self.head = item | 138 self.head.previous = self.head = item |
| 139 | 139 |
| 140 | 140 |
| 141 def flatten(items): | 141 def flatten(items): |
| 142 """Flattens a potentially nested sequence into a flat list: | 142 """Flattens a potentially nested sequence into a flat list. |
| 143 | |
| 144 :param items: the sequence to flatten | |
| 143 | 145 |
| 144 >>> flatten((1, 2)) | 146 >>> flatten((1, 2)) |
| 145 [1, 2] | 147 [1, 2] |
| 146 >>> flatten([1, (2, 3), 4]) | 148 >>> flatten([1, (2, 3), 4]) |
| 147 [1, 2, 3, 4] | 149 [1, 2, 3, 4] |
| 157 return retval | 159 return retval |
| 158 | 160 |
| 159 def plaintext(text, keeplinebreaks=True): | 161 def plaintext(text, keeplinebreaks=True): |
| 160 """Returns the text as a `unicode` string with all entities and tags | 162 """Returns the text as a `unicode` string with all entities and tags |
| 161 removed. | 163 removed. |
| 164 | |
| 165 >>> plaintext('<b>1 < 2</b>') | |
| 166 u'1 < 2' | |
| 167 | |
| 168 The `keeplinebreaks` parameter can be set to ``False`` to replace any line | |
| 169 breaks by simple spaces: | |
| 170 | |
| 171 >>> plaintext('''<b>1 | |
| 172 ... < | |
| 173 ... 2</b>''', keeplinebreaks=False) | |
| 174 u'1 < 2' | |
| 175 | |
| 176 :param text: the text to convert to plain text | |
| 177 :param keeplinebreaks: whether line breaks in the text should be kept intact | |
| 178 :return: the text with tags and entities removed | |
| 162 """ | 179 """ |
| 163 text = stripentities(striptags(text)) | 180 text = stripentities(striptags(text)) |
| 164 if not keeplinebreaks: | 181 if not keeplinebreaks: |
| 165 text = text.replace(u'\n', u' ') | 182 text = text.replace(u'\n', u' ') |
| 166 return text | 183 return text |
| 206 return ref | 223 return ref |
| 207 return _STRIPENTITIES_RE.sub(_replace_entity, text) | 224 return _STRIPENTITIES_RE.sub(_replace_entity, text) |
| 208 | 225 |
| 209 _STRIPTAGS_RE = re.compile(r'<[^>]*?>') | 226 _STRIPTAGS_RE = re.compile(r'<[^>]*?>') |
| 210 def striptags(text): | 227 def striptags(text): |
| 211 """Return a copy of the text with all XML/HTML tags removed. | 228 """Return a copy of the text with any XML/HTML tags removed. |
| 212 | 229 |
| 213 >>> striptags('<span>Foo</span> bar') | 230 >>> striptags('<span>Foo</span> bar') |
| 214 'Foo bar' | 231 'Foo bar' |
| 215 >>> striptags('<span class="bar">Foo</span>') | 232 >>> striptags('<span class="bar">Foo</span>') |
| 216 'Foo' | 233 'Foo' |
| 217 >>> striptags('Foo<br />') | 234 >>> striptags('Foo<br />') |
| 218 'Foo' | 235 'Foo' |
| 236 | |
| 237 :param text: the string to remove tags from | |
| 238 :return: the text with tags removed | |
| 219 """ | 239 """ |
| 220 return _STRIPTAGS_RE.sub('', text) | 240 return _STRIPTAGS_RE.sub('', text) |