Mercurial > p > roundup > code
comparison test/test_multipart.py @ 5306:91354bf0b683
Codecov showed text/html followed by text/plain not tested. Fixed bug
discovered.
The html part was double attached. Removed an unneeded attachment
call. Added some more test cases. Reworked test code to make selecting
html filter tool easier.
| author | John Rouillard <rouilj@ieee.org> |
|---|---|
| date | Fri, 13 Oct 2017 22:56:42 -0400 |
| parents | e20f472fde7d |
| children | 5b4931cfc182 |
comparison
equal
deleted
inserted
replaced
| 5305:e20f472fde7d | 5306:91354bf0b683 |
|---|---|
| 158 | 158 |
| 159 # end | 159 # end |
| 160 p = m.getpart() | 160 p = m.getpart() |
| 161 self.assert_(p is None) | 161 self.assert_(p is None) |
| 162 | 162 |
| 163 def TestExtraction(self, spec, expected): | 163 def TestExtraction(self, spec, expected, convert_html_with=False): |
| 164 from roundup.dehtml import dehtml | 164 if convert_html_with: |
| 165 from roundup.dehtml import dehtml | |
| 166 html2text=dehtml(convert_html_with).html2text | |
| 167 else: | |
| 168 html2text=None | |
| 165 | 169 |
| 166 self.assertEqual(ExampleMessage(spec).extract_content( | 170 self.assertEqual(ExampleMessage(spec).extract_content( |
| 167 html2text=dehtml('dhtml').html2text), expected) | 171 html2text=html2text), expected) |
| 168 | 172 |
| 169 def testTextPlain(self): | 173 def testTextPlain(self): |
| 170 self.TestExtraction('text/plain', ('foo\n', [], False)) | 174 self.TestExtraction('text/plain', ('foo\n', [], False)) |
| 171 | 175 |
| 172 def testAttachedTextPlain(self): | 176 def testAttachedTextPlain(self): |
| 184 application/pdf""", | 188 application/pdf""", |
| 185 ('foo\n', | 189 ('foo\n', |
| 186 [('foo.pdf', 'application/pdf', 'foo\n')], False)) | 190 [('foo.pdf', 'application/pdf', 'foo\n')], False)) |
| 187 | 191 |
| 188 def testMultipartMixedHtml(self): | 192 def testMultipartMixedHtml(self): |
| 193 # test with html conversion enabled | |
| 189 self.TestExtraction(""" | 194 self.TestExtraction(""" |
| 190 multipart/mixed | 195 multipart/mixed |
| 191 text/html | 196 text/html |
| 192 application/pdf""", | 197 application/pdf""", |
| 193 ('bar\n', | 198 ('bar\n', |
| 194 [('bar.html', 'text/html', | 199 [('bar.html', 'text/html', |
| 195 '<html><body>bar</body></html>\n'), | 200 '<html><body>bar</body></html>\n'), |
| 196 ('foo.pdf', 'application/pdf', 'foo\n')], False)) | 201 ('foo.pdf', 'application/pdf', 'foo\n')], False), |
| 202 convert_html_with='dehtml') | |
| 203 | |
| 204 # test with html conversion disabled | |
| 205 self.TestExtraction(""" | |
| 206 multipart/mixed | |
| 207 text/html | |
| 208 application/pdf""", | |
| 209 (None, | |
| 210 [('bar.html', 'text/html', | |
| 211 '<html><body>bar</body></html>\n'), | |
| 212 ('foo.pdf', 'application/pdf', 'foo\n')], False), | |
| 213 convert_html_with=False) | |
| 197 | 214 |
| 198 def testMultipartAlternative(self): | 215 def testMultipartAlternative(self): |
| 199 self.TestExtraction(""" | 216 self.TestExtraction(""" |
| 200 multipart/alternative | 217 multipart/alternative |
| 201 text/plain | 218 text/plain |
| 208 text/html | 225 text/html |
| 209 application/pdf""", | 226 application/pdf""", |
| 210 ('bar\n', | 227 ('bar\n', |
| 211 [('bar.html', 'text/html', | 228 [('bar.html', 'text/html', |
| 212 '<html><body>bar</body></html>\n'), | 229 '<html><body>bar</body></html>\n'), |
| 213 ('foo.pdf', 'application/pdf', 'foo\n')], False)) | 230 ('foo.pdf', 'application/pdf', 'foo\n')], False), |
| 231 convert_html_with='dehtml') | |
| 232 | |
| 233 self.TestExtraction(""" | |
| 234 multipart/alternative | |
| 235 text/html | |
| 236 application/pdf""", | |
| 237 (None, | |
| 238 [('bar.html', 'text/html', | |
| 239 '<html><body>bar</body></html>\n'), | |
| 240 ('foo.pdf', 'application/pdf', 'foo\n')], False), | |
| 241 convert_html_with=False) | |
| 242 | |
| 243 def testMultipartAlternativeHtmlText(self): | |
| 244 # text should take priority over html when html is first | |
| 245 self.TestExtraction(""" | |
| 246 multipart/alternative | |
| 247 text/html | |
| 248 text/plain | |
| 249 application/pdf""", | |
| 250 ('foo\n', | |
| 251 [('bar.html', 'text/html', | |
| 252 '<html><body>bar</body></html>\n'), | |
| 253 ('foo.pdf', 'application/pdf', 'foo\n')], False), | |
| 254 convert_html_with='dehtml') | |
| 255 | |
| 256 # text should take priority over html when text is first | |
| 257 self.TestExtraction(""" | |
| 258 multipart/alternative | |
| 259 text/plain | |
| 260 text/html | |
| 261 application/pdf""", | |
| 262 ('foo\n', | |
| 263 [('bar.html', 'text/html', | |
| 264 '<html><body>bar</body></html>\n'), | |
| 265 ('foo.pdf', 'application/pdf', 'foo\n')], False), | |
| 266 convert_html_with='dehtml') | |
| 267 | |
| 268 # text should take priority over html when text is second and | |
| 269 # html is disabled | |
| 270 self.TestExtraction(""" | |
| 271 multipart/alternative | |
| 272 text/html | |
| 273 text/plain | |
| 274 application/pdf""", | |
| 275 ('foo\n', | |
| 276 [('bar.html', 'text/html', | |
| 277 '<html><body>bar</body></html>\n'), | |
| 278 ('foo.pdf', 'application/pdf', 'foo\n')], False), | |
| 279 convert_html_with=False) | |
| 280 | |
| 281 # text should take priority over html when text is first and | |
| 282 # html is disabled | |
| 283 self.TestExtraction(""" | |
| 284 multipart/alternative | |
| 285 text/plain | |
| 286 text/html | |
| 287 application/pdf""", | |
| 288 ('foo\n', | |
| 289 [('bar.html', 'text/html', | |
| 290 '<html><body>bar</body></html>\n'), | |
| 291 ('foo.pdf', 'application/pdf', 'foo\n')], False), | |
| 292 convert_html_with=False) | |
| 214 | 293 |
| 215 def testDeepMultipartAlternative(self): | 294 def testDeepMultipartAlternative(self): |
| 216 self.TestExtraction(""" | 295 self.TestExtraction(""" |
| 217 multipart/mixed | 296 multipart/mixed |
| 218 multipart/alternative | 297 multipart/alternative |