Show More
@@ -182,7 +182,7 b' class GistsController(BaseController):' | |||||
182 | log.error(traceback.format_exc()) |
|
182 | log.error(traceback.format_exc()) | |
183 | raise HTTPNotFound() |
|
183 | raise HTTPNotFound() | |
184 | if format == 'raw': |
|
184 | if format == 'raw': | |
185 | content = '\n\n'.join([f.content for f in c.files if (f_path is None or safe_unicode(f.path) == f_path)]) |
|
185 | content = '\n\n'.join([safe_unicode(f.content) for f in c.files if (f_path is None or safe_unicode(f.path) == f_path)]) | |
186 | response.content_type = 'text/plain' |
|
186 | response.content_type = 'text/plain' | |
187 | return content |
|
187 | return content | |
188 | return render('admin/gists/show.html') |
|
188 | return render('admin/gists/show.html') |
@@ -272,7 +272,7 b' class CompareController(BaseRepoControll' | |||||
272 | ignore_whitespace=ignore_whitespace, |
|
272 | ignore_whitespace=ignore_whitespace, | |
273 | context=line_context) |
|
273 | context=line_context) | |
274 |
|
274 | |||
275 |
diff_processor = diffs.DiffProcessor(raw_diff |
|
275 | diff_processor = diffs.DiffProcessor(raw_diff, diff_limit=diff_limit) | |
276 | c.limited_diff = diff_processor.limited_diff |
|
276 | c.limited_diff = diff_processor.limited_diff | |
277 | c.file_diff_data = [] |
|
277 | c.file_diff_data = [] | |
278 | c.lines_added = 0 |
|
278 | c.lines_added = 0 |
@@ -94,7 +94,7 b' class FeedController(BaseRepoController)' | |||||
94 | desc_msg.extend(changes) |
|
94 | desc_msg.extend(changes) | |
95 | if str2bool(CONFIG.get('rss_include_diff', False)): |
|
95 | if str2bool(CONFIG.get('rss_include_diff', False)): | |
96 | desc_msg.append('\n\n') |
|
96 | desc_msg.append('\n\n') | |
97 | desc_msg.append(raw_diff) |
|
97 | desc_msg.append(safe_unicode(raw_diff)) | |
98 | desc_msg.append('</pre>') |
|
98 | desc_msg.append('</pre>') | |
99 | return [safe_unicode(chunk) for chunk in desc_msg] |
|
99 | return [safe_unicode(chunk) for chunk in desc_msg] | |
100 |
|
100 |
@@ -46,7 +46,7 b' from kallithea.lib.auth import HasRepoPe' | |||||
46 | from kallithea.lib.base import BaseRepoController, jsonify, render |
|
46 | from kallithea.lib.base import BaseRepoController, jsonify, render | |
47 | from kallithea.lib.exceptions import NonRelativePathError |
|
47 | from kallithea.lib.exceptions import NonRelativePathError | |
48 | from kallithea.lib.utils import action_logger |
|
48 | from kallithea.lib.utils import action_logger | |
49 | from kallithea.lib.utils2 import convert_line_endings, detect_mode, safe_int, safe_str, str2bool |
|
49 | from kallithea.lib.utils2 import convert_line_endings, detect_mode, safe_int, safe_str, safe_unicode, str2bool | |
50 | from kallithea.lib.vcs.backends.base import EmptyChangeset |
|
50 | from kallithea.lib.vcs.backends.base import EmptyChangeset | |
51 | from kallithea.lib.vcs.conf import settings |
|
51 | from kallithea.lib.vcs.conf import settings | |
52 | from kallithea.lib.vcs.exceptions import ( |
|
52 | from kallithea.lib.vcs.exceptions import ( | |
@@ -365,8 +365,7 b' class FilesController(BaseRepoController' | |||||
365 | c.f_path = f_path |
|
365 | c.f_path = f_path | |
366 |
|
366 | |||
367 | if r_post: |
|
367 | if r_post: | |
368 |
|
368 | old_content = safe_unicode(c.file.content) | ||
369 | old_content = c.file.content |
|
|||
370 | sl = old_content.splitlines(1) |
|
369 | sl = old_content.splitlines(1) | |
371 | first_line = sl[0] if sl else '' |
|
370 | first_line = sl[0] if sl else '' | |
372 | # modes: 0 - Unix, 1 - Mac, 2 - DOS |
|
371 | # modes: 0 - Unix, 1 - Mac, 2 - DOS |
@@ -591,7 +591,7 b' class PullrequestsController(BaseRepoCon' | |||||
591 | ignore_whitespace=ignore_whitespace, context=line_context) |
|
591 | ignore_whitespace=ignore_whitespace, context=line_context) | |
592 | except ChangesetDoesNotExistError: |
|
592 | except ChangesetDoesNotExistError: | |
593 | raw_diff = _("The diff can't be shown - the PR revisions could not be found.") |
|
593 | raw_diff = _("The diff can't be shown - the PR revisions could not be found.") | |
594 |
diff_processor = diffs.DiffProcessor(raw_diff |
|
594 | diff_processor = diffs.DiffProcessor(raw_diff, diff_limit=diff_limit) | |
595 | c.limited_diff = diff_processor.limited_diff |
|
595 | c.limited_diff = diff_processor.limited_diff | |
596 | c.file_diff_data = [] |
|
596 | c.file_diff_data = [] | |
597 | c.lines_added = 0 |
|
597 | c.lines_added = 0 |
@@ -46,7 +46,7 b' from kallithea.lib.celerylib.tasks impor' | |||||
46 | from kallithea.lib.compat import json |
|
46 | from kallithea.lib.compat import json | |
47 | from kallithea.lib.markup_renderer import MarkupRenderer |
|
47 | from kallithea.lib.markup_renderer import MarkupRenderer | |
48 | from kallithea.lib.page import Page |
|
48 | from kallithea.lib.page import Page | |
49 | from kallithea.lib.utils2 import safe_int |
|
49 | from kallithea.lib.utils2 import safe_int, safe_unicode | |
50 | from kallithea.lib.vcs.backends.base import EmptyChangeset |
|
50 | from kallithea.lib.vcs.backends.base import EmptyChangeset | |
51 | from kallithea.lib.vcs.exceptions import ChangesetError, EmptyRepositoryError, NodeDoesNotExistError |
|
51 | from kallithea.lib.vcs.exceptions import ChangesetError, EmptyRepositoryError, NodeDoesNotExistError | |
52 | from kallithea.lib.vcs.nodes import FileNode |
|
52 | from kallithea.lib.vcs.nodes import FileNode | |
@@ -84,7 +84,7 b' class SummaryController(BaseRepoControll' | |||||
84 | readme_file = f |
|
84 | readme_file = f | |
85 | log.debug('Found README file `%s` rendering...', |
|
85 | log.debug('Found README file `%s` rendering...', | |
86 | readme_file) |
|
86 | readme_file) | |
87 | readme_data = renderer.render(readme.content, |
|
87 | readme_data = renderer.render(safe_unicode(readme.content), | |
88 | filename=f) |
|
88 | filename=f) | |
89 | break |
|
89 | break | |
90 | except NodeDoesNotExistError: |
|
90 | except NodeDoesNotExistError: |
@@ -30,6 +30,7 b' from pygments.formatters import HtmlForm' | |||||
30 |
|
30 | |||
31 | from kallithea.lib.vcs.exceptions import VCSError |
|
31 | from kallithea.lib.vcs.exceptions import VCSError | |
32 | from kallithea.lib.vcs.nodes import FileNode |
|
32 | from kallithea.lib.vcs.nodes import FileNode | |
|
33 | from kallithea.lib.vcs.utils import safe_unicode | |||
33 |
|
34 | |||
34 |
|
35 | |||
35 | def annotate_highlight(filenode, annotate_from_changeset_func=None, |
|
36 | def annotate_highlight(filenode, annotate_from_changeset_func=None, | |
@@ -53,7 +54,7 b' def annotate_highlight(filenode, annotat' | |||||
53 | headers=headers, |
|
54 | headers=headers, | |
54 | annotate_from_changeset_func=annotate_from_changeset_func, **options) |
|
55 | annotate_from_changeset_func=annotate_from_changeset_func, **options) | |
55 | lexer = get_custom_lexer(filenode.extension) or filenode.lexer |
|
56 | lexer = get_custom_lexer(filenode.extension) or filenode.lexer | |
56 | highlighted = highlight(filenode.content, lexer, formatter) |
|
57 | highlighted = highlight(safe_unicode(filenode.content), lexer, formatter) | |
57 | return highlighted |
|
58 | return highlighted | |
58 |
|
59 | |||
59 |
|
60 |
@@ -289,8 +289,8 b' class DiffProcessor(object):' | |||||
289 | based on that parameter cut off will be triggered, set to None |
|
289 | based on that parameter cut off will be triggered, set to None | |
290 | to show full diff |
|
290 | to show full diff | |
291 | """ |
|
291 | """ | |
292 |
if not isinstance(diff, b |
|
292 | if not isinstance(diff, bytes): | |
293 |
raise Exception('Diff must be |
|
293 | raise Exception('Diff must be bytes - got %s' % type(diff)) | |
294 |
|
294 | |||
295 | self._diff = diff |
|
295 | self._diff = diff | |
296 | self.adds = 0 |
|
296 | self.adds = 0 | |
@@ -516,6 +516,9 b' def _escaper(string):' | |||||
516 | """, re.VERBOSE | re.MULTILINE) |
|
516 | """, re.VERBOSE | re.MULTILINE) | |
517 |
|
517 | |||
518 |
|
518 | |||
|
519 | _header_next_check = re.compile(br'''(?!@)(?!literal )(?!delta )''') | |||
|
520 | ||||
|
521 | ||||
519 | def _get_header(vcs, diff_chunk): |
|
522 | def _get_header(vcs, diff_chunk): | |
520 | """ |
|
523 | """ | |
521 | Parses a Git diff for a single file (header and chunks) and returns a tuple with: |
|
524 | Parses a Git diff for a single file (header and chunks) and returns a tuple with: | |
@@ -537,7 +540,7 b' def _get_header(vcs, diff_chunk):' | |||||
537 | raise Exception('diff not recognized as valid %s diff' % vcs) |
|
540 | raise Exception('diff not recognized as valid %s diff' % vcs) | |
538 | meta_info = match.groupdict() |
|
541 | meta_info = match.groupdict() | |
539 | rest = diff_chunk[match.end():] |
|
542 | rest = diff_chunk[match.end():] | |
540 | if rest and not rest.startswith('@') and not rest.startswith('literal ') and not rest.startswith('delta '): |
|
543 | if rest and _header_next_check.match(rest): | |
541 | raise Exception('cannot parse %s diff header: %r followed by %r' % (vcs, diff_chunk[:match.end()], rest[:1000])) |
|
544 | raise Exception('cannot parse %s diff header: %r followed by %r' % (vcs, diff_chunk[:match.end()], rest[:1000])) | |
542 | diff_lines = (_escaper(m.group(0)) for m in re.finditer(r'.*\n|.+$', rest)) # don't split on \r as str.splitlines do |
|
545 | diff_lines = (_escaper(m.group(0)) for m in re.finditer(r'.*\n|.+$', rest)) # don't split on \r as str.splitlines do | |
543 | return meta_info, diff_lines |
|
546 | return meta_info, diff_lines |
@@ -330,7 +330,7 b' def pygmentize(filenode, **kwargs):' | |||||
330 | """ |
|
330 | """ | |
331 | lexer = get_custom_lexer(filenode.extension) or filenode.lexer |
|
331 | lexer = get_custom_lexer(filenode.extension) or filenode.lexer | |
332 | return literal(markup_whitespace( |
|
332 | return literal(markup_whitespace( | |
333 | code_highlight(filenode.content, lexer, CodeHtmlFormatter(**kwargs)))) |
|
333 | code_highlight(safe_unicode(filenode.content), lexer, CodeHtmlFormatter(**kwargs)))) | |
334 |
|
334 | |||
335 |
|
335 | |||
336 | def pygmentize_annotation(repo_name, filenode, **kwargs): |
|
336 | def pygmentize_annotation(repo_name, filenode, **kwargs): |
@@ -182,12 +182,13 b' class WhooshIndexingDaemon(object):' | |||||
182 |
|
182 | |||
183 | indexed = indexed_w_content = 0 |
|
183 | indexed = indexed_w_content = 0 | |
184 | if self.is_indexable_node(node): |
|
184 | if self.is_indexable_node(node): | |
185 |
|
|
185 | bytes_content = node.content | |
186 |
if |
|
186 | if b'\0' in bytes_content: | |
187 | log.warning(' >> %s - no text content', path) |
|
187 | log.warning(' >> %s - no text content', path) | |
188 | u_content = u'' |
|
188 | u_content = u'' | |
189 | else: |
|
189 | else: | |
190 | log.debug(' >> %s', path) |
|
190 | log.debug(' >> %s', path) | |
|
191 | u_content = safe_unicode(bytes_content) | |||
191 | indexed_w_content += 1 |
|
192 | indexed_w_content += 1 | |
192 |
|
193 | |||
193 | else: |
|
194 | else: |
@@ -68,11 +68,7 b' class GitInMemoryChangeset(BaseInMemoryC' | |||||
68 | # for dirnames (in reverse order) [this only applies for nodes from added] |
|
68 | # for dirnames (in reverse order) [this only applies for nodes from added] | |
69 | new_trees = [] |
|
69 | new_trees = [] | |
70 |
|
70 | |||
71 | if not node.is_binary: |
|
71 | blob = objects.Blob.from_string(node.content) | |
72 | content = node.content.encode(ENCODING) |
|
|||
73 | else: |
|
|||
74 | content = node.content |
|
|||
75 | blob = objects.Blob.from_string(content) |
|
|||
76 |
|
72 | |||
77 | node_path = safe_bytes(node.name) |
|
73 | node_path = safe_bytes(node.name) | |
78 | if dirnames: |
|
74 | if dirnames: |
@@ -52,8 +52,7 b' class MercurialInMemoryChangeset(BaseInM' | |||||
52 | for node in self.added: |
|
52 | for node in self.added: | |
53 | if node.path == path: |
|
53 | if node.path == path: | |
54 | return memfilectx(_repo, memctx, path=node.path, |
|
54 | return memfilectx(_repo, memctx, path=node.path, | |
55 |
data= |
|
55 | data=node.content, | |
56 | if not node.is_binary else node.content), |
|
|||
57 | islink=False, |
|
56 | islink=False, | |
58 | isexec=node.is_executable, |
|
57 | isexec=node.is_executable, | |
59 | copysource=False) |
|
58 | copysource=False) | |
@@ -62,8 +61,7 b' class MercurialInMemoryChangeset(BaseInM' | |||||
62 | for node in self.changed: |
|
61 | for node in self.changed: | |
63 | if node.path == path: |
|
62 | if node.path == path: | |
64 | return memfilectx(_repo, memctx, path=node.path, |
|
63 | return memfilectx(_repo, memctx, path=node.path, | |
65 |
data= |
|
64 | data=node.content, | |
66 | if not node.is_binary else node.content), |
|
|||
67 | islink=False, |
|
65 | islink=False, | |
68 | isexec=node.is_executable, |
|
66 | isexec=node.is_executable, | |
69 | copysource=False) |
|
67 | copysource=False) |
@@ -16,7 +16,7 b' import stat' | |||||
16 |
|
16 | |||
17 | from kallithea.lib.vcs.backends.base import EmptyChangeset |
|
17 | from kallithea.lib.vcs.backends.base import EmptyChangeset | |
18 | from kallithea.lib.vcs.exceptions import NodeError, RemovedFileNodeError |
|
18 | from kallithea.lib.vcs.exceptions import NodeError, RemovedFileNodeError | |
19 | from kallithea.lib.vcs.utils import safe_str, safe_unicode |
|
19 | from kallithea.lib.vcs.utils import safe_bytes, safe_str, safe_unicode | |
20 | from kallithea.lib.vcs.utils.lazy import LazyProperty |
|
20 | from kallithea.lib.vcs.utils.lazy import LazyProperty | |
21 |
|
21 | |||
22 |
|
22 | |||
@@ -263,6 +263,10 b' class FileNode(Node):' | |||||
263 | raise NodeError("Cannot use both content and changeset") |
|
263 | raise NodeError("Cannot use both content and changeset") | |
264 | super(FileNode, self).__init__(path, kind=NodeKind.FILE) |
|
264 | super(FileNode, self).__init__(path, kind=NodeKind.FILE) | |
265 | self.changeset = changeset |
|
265 | self.changeset = changeset | |
|
266 | if not isinstance(content, bytes) and content is not None: | |||
|
267 | # File content is one thing that inherently must be bytes ... but | |||
|
268 | # VCS module tries to be "user friendly" and support unicode ... | |||
|
269 | content = safe_bytes(content) | |||
266 | self._content = content |
|
270 | self._content = content | |
267 | self._mode = mode or 0o100644 |
|
271 | self._mode = mode or 0o100644 | |
268 |
|
272 | |||
@@ -278,25 +282,17 b' class FileNode(Node):' | |||||
278 | mode = self._mode |
|
282 | mode = self._mode | |
279 | return mode |
|
283 | return mode | |
280 |
|
284 | |||
281 | def _get_content(self): |
|
285 | @property | |
|
286 | def content(self): | |||
|
287 | """ | |||
|
288 | Returns lazily byte content of the FileNode. | |||
|
289 | """ | |||
282 | if self.changeset: |
|
290 | if self.changeset: | |
283 | content = self.changeset.get_file_content(self.path) |
|
291 | content = self.changeset.get_file_content(self.path) | |
284 | else: |
|
292 | else: | |
285 | content = self._content |
|
293 | content = self._content | |
286 | return content |
|
294 | return content | |
287 |
|
295 | |||
288 | @property |
|
|||
289 | def content(self): |
|
|||
290 | """ |
|
|||
291 | Returns lazily content of the FileNode. If possible, would try to |
|
|||
292 | decode content from UTF-8. |
|
|||
293 | """ |
|
|||
294 | content = self._get_content() |
|
|||
295 |
|
||||
296 | if bool(content and '\0' in content): |
|
|||
297 | return content |
|
|||
298 | return safe_unicode(content) |
|
|||
299 |
|
||||
300 | @LazyProperty |
|
296 | @LazyProperty | |
301 | def size(self): |
|
297 | def size(self): | |
302 | if self.changeset: |
|
298 | if self.changeset: | |
@@ -366,7 +362,7 b' class FileNode(Node):' | |||||
366 | """ |
|
362 | """ | |
367 | from pygments import lexers |
|
363 | from pygments import lexers | |
368 | try: |
|
364 | try: | |
369 | lexer = lexers.guess_lexer_for_filename(self.name, self.content, stripnl=False) |
|
365 | lexer = lexers.guess_lexer_for_filename(self.name, safe_unicode(self.content), stripnl=False) | |
370 | except lexers.ClassNotFound: |
|
366 | except lexers.ClassNotFound: | |
371 | lexer = lexers.TextLexer(stripnl=False) |
|
367 | lexer = lexers.TextLexer(stripnl=False) | |
372 | # returns first alias |
|
368 | # returns first alias | |
@@ -414,8 +410,7 b' class FileNode(Node):' | |||||
414 | """ |
|
410 | """ | |
415 | Returns True if file has binary content. |
|
411 | Returns True if file has binary content. | |
416 | """ |
|
412 | """ | |
417 |
|
|
413 | return b'\0' in self.content | |
418 | return _bin |
|
|||
419 |
|
414 | |||
420 | def is_browser_compatible_image(self): |
|
415 | def is_browser_compatible_image(self): | |
421 | return self.mimetype in [ |
|
416 | return self.mimetype in [ |
@@ -3,6 +3,7 b' from pygments.formatters import HtmlForm' | |||||
3 |
|
3 | |||
4 | from kallithea.lib.vcs.exceptions import VCSError |
|
4 | from kallithea.lib.vcs.exceptions import VCSError | |
5 | from kallithea.lib.vcs.nodes import FileNode |
|
5 | from kallithea.lib.vcs.nodes import FileNode | |
|
6 | from kallithea.lib.vcs.utils import safe_unicode | |||
6 |
|
7 | |||
7 |
|
8 | |||
8 | def annotate_highlight(filenode, annotate_from_changeset_func=None, |
|
9 | def annotate_highlight(filenode, annotate_from_changeset_func=None, | |
@@ -24,9 +25,7 b' def annotate_highlight(filenode, annotat' | |||||
24 | formatter = AnnotateHtmlFormatter(filenode=filenode, order=order, |
|
25 | formatter = AnnotateHtmlFormatter(filenode=filenode, order=order, | |
25 | headers=headers, |
|
26 | headers=headers, | |
26 | annotate_from_changeset_func=annotate_from_changeset_func, **options) |
|
27 | annotate_from_changeset_func=annotate_from_changeset_func, **options) | |
27 | lexer = filenode.lexer |
|
28 | return highlight(safe_unicode(filenode.content), filenode.lexer, formatter) | |
28 | highlighted = highlight(filenode.content, lexer, formatter) |
|
|||
29 | return highlighted |
|
|||
30 |
|
29 | |||
31 |
|
30 | |||
32 | class AnnotateHtmlFormatter(HtmlFormatter): |
|
31 | class AnnotateHtmlFormatter(HtmlFormatter): |
@@ -73,7 +73,7 b'' | |||||
73 | </div> |
|
73 | </div> | |
74 | <div class="panel-body no-padding"> |
|
74 | <div class="panel-body no-padding"> | |
75 | <div id="editor_container"> |
|
75 | <div id="editor_container"> | |
76 | <textarea id="editor_${h.FID('f',file.path)}" name="contents" style="display:none">${file.content}</textarea> |
|
76 | <textarea id="editor_${h.FID('f',file.path)}" name="contents" style="display:none">${safe_unicode(file.content)}</textarea> | |
77 | </div> |
|
77 | </div> | |
78 | </div> |
|
78 | </div> | |
79 | </div> |
|
79 | </div> |
@@ -59,7 +59,7 b'' | |||||
59 | </span> |
|
59 | </span> | |
60 | </div> |
|
60 | </div> | |
61 | <div class="panel-body no-padding"> |
|
61 | <div class="panel-body no-padding"> | |
62 | <textarea id="editor" name="content" style="display:none">${h.escape(c.file.content)|n}</textarea> |
|
62 | <textarea id="editor" name="content" style="display:none">${h.escape(safe_unicode(c.file.content))|n}</textarea> | |
63 | </div> |
|
63 | </div> | |
64 | </div> |
|
64 | </div> | |
65 | <div> |
|
65 | <div> |
@@ -596,11 +596,11 b' class TestGitChangeset(object):' | |||||
596 | for cs in self.repo: |
|
596 | for cs in self.repo: | |
597 | assert isinstance(cs.author, unicode) |
|
597 | assert isinstance(cs.author, unicode) | |
598 |
|
598 | |||
599 |
def test_repo_files_content_is_ |
|
599 | def test_repo_files_content_is_bytes(self): | |
600 | changeset = self.repo.get_changeset() |
|
600 | changeset = self.repo.get_changeset() | |
601 | for node in changeset.get_node('/'): |
|
601 | for node in changeset.get_node('/'): | |
602 | if node.is_file(): |
|
602 | if node.is_file(): | |
603 |
assert isinstance(node.content, |
|
603 | assert isinstance(node.content, bytes) | |
604 |
|
604 | |||
605 | def test_wrong_path(self): |
|
605 | def test_wrong_path(self): | |
606 | # There is 'setup.py' in the root dir but not there: |
|
606 | # There is 'setup.py' in the root dir but not there: |
@@ -544,11 +544,11 b' class TestMercurialChangeset(object):' | |||||
544 | for cm in self.repo: |
|
544 | for cm in self.repo: | |
545 | assert isinstance(cm.author, unicode) |
|
545 | assert isinstance(cm.author, unicode) | |
546 |
|
546 | |||
547 |
def test_repo_files_content_is_ |
|
547 | def test_repo_files_content_is_bytes(self): | |
548 | test_changeset = self.repo.get_changeset(100) |
|
548 | test_changeset = self.repo.get_changeset(100) | |
549 | for node in test_changeset.get_node('/'): |
|
549 | for node in test_changeset.get_node('/'): | |
550 | if node.is_file(): |
|
550 | if node.is_file(): | |
551 |
assert isinstance(node.content, |
|
551 | assert isinstance(node.content, bytes) | |
552 |
|
552 | |||
553 | def test_wrong_path(self): |
|
553 | def test_wrong_path(self): | |
554 | # There is 'setup.py' in the root dir but not there: |
|
554 | # There is 'setup.py' in the root dir but not there: |
General Comments 0
You need to be logged in to leave comments.
Login now