Show More
@@ -1,545 +1,545 b'' | |||||
1 | # -*- coding: utf-8 -*- |
|
1 | # -*- coding: utf-8 -*- | |
2 | # This program is free software: you can redistribute it and/or modify |
|
2 | # This program is free software: you can redistribute it and/or modify | |
3 | # it under the terms of the GNU General Public License as published by |
|
3 | # it under the terms of the GNU General Public License as published by | |
4 | # the Free Software Foundation, either version 3 of the License, or |
|
4 | # the Free Software Foundation, either version 3 of the License, or | |
5 | # (at your option) any later version. |
|
5 | # (at your option) any later version. | |
6 | # |
|
6 | # | |
7 | # This program is distributed in the hope that it will be useful, |
|
7 | # This program is distributed in the hope that it will be useful, | |
8 | # but WITHOUT ANY WARRANTY; without even the implied warranty of |
|
8 | # but WITHOUT ANY WARRANTY; without even the implied warranty of | |
9 | # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the |
|
9 | # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the | |
10 | # GNU General Public License for more details. |
|
10 | # GNU General Public License for more details. | |
11 | # |
|
11 | # | |
12 | # You should have received a copy of the GNU General Public License |
|
12 | # You should have received a copy of the GNU General Public License | |
13 | # along with this program. If not, see <http://www.gnu.org/licenses/>. |
|
13 | # along with this program. If not, see <http://www.gnu.org/licenses/>. | |
14 | """ |
|
14 | """ | |
15 | kallithea.lib.utils2 |
|
15 | kallithea.lib.utils2 | |
16 | ~~~~~~~~~~~~~~~~~~~~ |
|
16 | ~~~~~~~~~~~~~~~~~~~~ | |
17 |
|
17 | |||
18 | Some simple helper functions. |
|
18 | Some simple helper functions. | |
19 | Note: all these functions should be independent of Kallithea classes, i.e. |
|
19 | Note: all these functions should be independent of Kallithea classes, i.e. | |
20 | models, controllers, etc. to prevent import cycles. |
|
20 | models, controllers, etc. to prevent import cycles. | |
21 |
|
21 | |||
22 | This file was forked by the Kallithea project in July 2014. |
|
22 | This file was forked by the Kallithea project in July 2014. | |
23 | Original author and date, and relevant copyright and licensing information is below: |
|
23 | Original author and date, and relevant copyright and licensing information is below: | |
24 | :created_on: Jan 5, 2011 |
|
24 | :created_on: Jan 5, 2011 | |
25 | :author: marcink |
|
25 | :author: marcink | |
26 | :copyright: (c) 2013 RhodeCode GmbH, and others. |
|
26 | :copyright: (c) 2013 RhodeCode GmbH, and others. | |
27 | :license: GPLv3, see LICENSE.md for more details. |
|
27 | :license: GPLv3, see LICENSE.md for more details. | |
28 | """ |
|
28 | """ | |
29 |
|
29 | |||
30 | import binascii |
|
30 | import binascii | |
31 | import datetime |
|
31 | import datetime | |
32 | import hashlib |
|
32 | import hashlib | |
33 | import json |
|
33 | import json | |
34 | import logging |
|
34 | import logging | |
35 | import os |
|
35 | import os | |
36 | import re |
|
36 | import re | |
37 | import string |
|
37 | import string | |
38 | import sys |
|
38 | import sys | |
39 | import time |
|
39 | import time | |
40 | import urllib.parse |
|
40 | import urllib.parse | |
41 | from distutils.version import StrictVersion |
|
|||
42 |
|
41 | |||
43 | import bcrypt |
|
42 | import bcrypt | |
44 | import urlobject |
|
43 | import urlobject | |
|
44 | from packaging.version import Version | |||
45 | from sqlalchemy.engine import url as sa_url |
|
45 | from sqlalchemy.engine import url as sa_url | |
46 | from sqlalchemy.exc import ArgumentError |
|
46 | from sqlalchemy.exc import ArgumentError | |
47 | from tg import tmpl_context |
|
47 | from tg import tmpl_context | |
48 | from tg.support.converters import asbool, aslist |
|
48 | from tg.support.converters import asbool, aslist | |
49 | from webhelpers2.text import collapse, remove_formatting, strip_tags |
|
49 | from webhelpers2.text import collapse, remove_formatting, strip_tags | |
50 |
|
50 | |||
51 | import kallithea |
|
51 | import kallithea | |
52 | from kallithea.lib import webutils |
|
52 | from kallithea.lib import webutils | |
53 | from kallithea.lib.vcs.backends.base import BaseRepository, EmptyChangeset |
|
53 | from kallithea.lib.vcs.backends.base import BaseRepository, EmptyChangeset | |
54 | from kallithea.lib.vcs.backends.git.repository import GitRepository |
|
54 | from kallithea.lib.vcs.backends.git.repository import GitRepository | |
55 | from kallithea.lib.vcs.conf import settings |
|
55 | from kallithea.lib.vcs.conf import settings | |
56 | from kallithea.lib.vcs.exceptions import RepositoryError |
|
56 | from kallithea.lib.vcs.exceptions import RepositoryError | |
57 | from kallithea.lib.vcs.utils import ascii_bytes, ascii_str, safe_bytes, safe_str # re-export |
|
57 | from kallithea.lib.vcs.utils import ascii_bytes, ascii_str, safe_bytes, safe_str # re-export | |
58 | from kallithea.lib.vcs.utils.lazy import LazyProperty |
|
58 | from kallithea.lib.vcs.utils.lazy import LazyProperty | |
59 |
|
59 | |||
60 |
|
60 | |||
61 | try: |
|
61 | try: | |
62 | import pwd |
|
62 | import pwd | |
63 | except ImportError: |
|
63 | except ImportError: | |
64 | pass |
|
64 | pass | |
65 |
|
65 | |||
66 |
|
66 | |||
67 | log = logging.getLogger(__name__) |
|
67 | log = logging.getLogger(__name__) | |
68 |
|
68 | |||
69 |
|
69 | |||
70 | # mute pyflakes "imported but unused" |
|
70 | # mute pyflakes "imported but unused" | |
71 | assert asbool |
|
71 | assert asbool | |
72 | assert aslist |
|
72 | assert aslist | |
73 | assert ascii_bytes |
|
73 | assert ascii_bytes | |
74 | assert ascii_str |
|
74 | assert ascii_str | |
75 | assert safe_bytes |
|
75 | assert safe_bytes | |
76 | assert safe_str |
|
76 | assert safe_str | |
77 | assert LazyProperty |
|
77 | assert LazyProperty | |
78 |
|
78 | |||
79 |
|
79 | |||
80 | # get current umask value without changing it |
|
80 | # get current umask value without changing it | |
81 | umask = os.umask(0) |
|
81 | umask = os.umask(0) | |
82 | os.umask(umask) |
|
82 | os.umask(umask) | |
83 |
|
83 | |||
84 |
|
84 | |||
85 | def convert_line_endings(line, mode): |
|
85 | def convert_line_endings(line, mode): | |
86 | """ |
|
86 | """ | |
87 | Converts a given line "line end" according to given mode |
|
87 | Converts a given line "line end" according to given mode | |
88 |
|
88 | |||
89 | Available modes are:: |
|
89 | Available modes are:: | |
90 | 0 - Unix |
|
90 | 0 - Unix | |
91 | 1 - Mac |
|
91 | 1 - Mac | |
92 | 2 - DOS |
|
92 | 2 - DOS | |
93 |
|
93 | |||
94 | :param line: given line to convert |
|
94 | :param line: given line to convert | |
95 | :param mode: mode to convert to |
|
95 | :param mode: mode to convert to | |
96 | :rtype: str |
|
96 | :rtype: str | |
97 | :return: converted line according to mode |
|
97 | :return: converted line according to mode | |
98 | """ |
|
98 | """ | |
99 | if mode == 0: |
|
99 | if mode == 0: | |
100 | line = line.replace('\r\n', '\n') |
|
100 | line = line.replace('\r\n', '\n') | |
101 | line = line.replace('\r', '\n') |
|
101 | line = line.replace('\r', '\n') | |
102 | elif mode == 1: |
|
102 | elif mode == 1: | |
103 | line = line.replace('\r\n', '\r') |
|
103 | line = line.replace('\r\n', '\r') | |
104 | line = line.replace('\n', '\r') |
|
104 | line = line.replace('\n', '\r') | |
105 | elif mode == 2: |
|
105 | elif mode == 2: | |
106 | line = re.sub("\r(?!\n)|(?<!\r)\n", "\r\n", line) |
|
106 | line = re.sub("\r(?!\n)|(?<!\r)\n", "\r\n", line) | |
107 | return line |
|
107 | return line | |
108 |
|
108 | |||
109 |
|
109 | |||
110 | def detect_mode(line, default): |
|
110 | def detect_mode(line, default): | |
111 | """ |
|
111 | """ | |
112 | Detects line break for given line, if line break couldn't be found |
|
112 | Detects line break for given line, if line break couldn't be found | |
113 | given default value is returned |
|
113 | given default value is returned | |
114 |
|
114 | |||
115 | :param line: str line |
|
115 | :param line: str line | |
116 | :param default: default |
|
116 | :param default: default | |
117 | :rtype: int |
|
117 | :rtype: int | |
118 | :return: value of line end on of 0 - Unix, 1 - Mac, 2 - DOS |
|
118 | :return: value of line end on of 0 - Unix, 1 - Mac, 2 - DOS | |
119 | """ |
|
119 | """ | |
120 | if line.endswith('\r\n'): |
|
120 | if line.endswith('\r\n'): | |
121 | return 2 |
|
121 | return 2 | |
122 | elif line.endswith('\n'): |
|
122 | elif line.endswith('\n'): | |
123 | return 0 |
|
123 | return 0 | |
124 | elif line.endswith('\r'): |
|
124 | elif line.endswith('\r'): | |
125 | return 1 |
|
125 | return 1 | |
126 | else: |
|
126 | else: | |
127 | return default |
|
127 | return default | |
128 |
|
128 | |||
129 |
|
129 | |||
130 | def generate_api_key(): |
|
130 | def generate_api_key(): | |
131 | """ |
|
131 | """ | |
132 | Generates a random (presumably unique) API key. |
|
132 | Generates a random (presumably unique) API key. | |
133 |
|
133 | |||
134 | This value is used in URLs and "Bearer" HTTP Authorization headers, |
|
134 | This value is used in URLs and "Bearer" HTTP Authorization headers, | |
135 | which in practice means it should only contain URL-safe characters |
|
135 | which in practice means it should only contain URL-safe characters | |
136 | (RFC 3986): |
|
136 | (RFC 3986): | |
137 |
|
137 | |||
138 | unreserved = ALPHA / DIGIT / "-" / "." / "_" / "~" |
|
138 | unreserved = ALPHA / DIGIT / "-" / "." / "_" / "~" | |
139 | """ |
|
139 | """ | |
140 | # Hexadecimal certainly qualifies as URL-safe. |
|
140 | # Hexadecimal certainly qualifies as URL-safe. | |
141 | return ascii_str(binascii.hexlify(os.urandom(20))) |
|
141 | return ascii_str(binascii.hexlify(os.urandom(20))) | |
142 |
|
142 | |||
143 |
|
143 | |||
144 | def safe_int(val, default=None): |
|
144 | def safe_int(val, default=None): | |
145 | """ |
|
145 | """ | |
146 | Returns int() of val if val is not convertable to int use default |
|
146 | Returns int() of val if val is not convertable to int use default | |
147 | instead |
|
147 | instead | |
148 |
|
148 | |||
149 | :param val: |
|
149 | :param val: | |
150 | :param default: |
|
150 | :param default: | |
151 | """ |
|
151 | """ | |
152 | try: |
|
152 | try: | |
153 | val = int(val) |
|
153 | val = int(val) | |
154 | except (ValueError, TypeError): |
|
154 | except (ValueError, TypeError): | |
155 | val = default |
|
155 | val = default | |
156 | return val |
|
156 | return val | |
157 |
|
157 | |||
158 |
|
158 | |||
159 | def remove_suffix(s, suffix): |
|
159 | def remove_suffix(s, suffix): | |
160 | if s.endswith(suffix): |
|
160 | if s.endswith(suffix): | |
161 | s = s[:-1 * len(suffix)] |
|
161 | s = s[:-1 * len(suffix)] | |
162 | return s |
|
162 | return s | |
163 |
|
163 | |||
164 |
|
164 | |||
165 | def remove_prefix(s, prefix): |
|
165 | def remove_prefix(s, prefix): | |
166 | if s.startswith(prefix): |
|
166 | if s.startswith(prefix): | |
167 | s = s[len(prefix):] |
|
167 | s = s[len(prefix):] | |
168 | return s |
|
168 | return s | |
169 |
|
169 | |||
170 |
|
170 | |||
171 | def uri_filter(uri): |
|
171 | def uri_filter(uri): | |
172 | """ |
|
172 | """ | |
173 | Removes user:password from given url string |
|
173 | Removes user:password from given url string | |
174 |
|
174 | |||
175 | :param uri: |
|
175 | :param uri: | |
176 | :rtype: str |
|
176 | :rtype: str | |
177 | :returns: filtered list of strings |
|
177 | :returns: filtered list of strings | |
178 | """ |
|
178 | """ | |
179 | if not uri: |
|
179 | if not uri: | |
180 | return [] |
|
180 | return [] | |
181 |
|
181 | |||
182 | proto = '' |
|
182 | proto = '' | |
183 |
|
183 | |||
184 | for pat in ('https://', 'http://', 'git://'): |
|
184 | for pat in ('https://', 'http://', 'git://'): | |
185 | if uri.startswith(pat): |
|
185 | if uri.startswith(pat): | |
186 | uri = uri[len(pat):] |
|
186 | uri = uri[len(pat):] | |
187 | proto = pat |
|
187 | proto = pat | |
188 | break |
|
188 | break | |
189 |
|
189 | |||
190 | # remove passwords and username |
|
190 | # remove passwords and username | |
191 | uri = uri[uri.find('@') + 1:] |
|
191 | uri = uri[uri.find('@') + 1:] | |
192 |
|
192 | |||
193 | # get the port |
|
193 | # get the port | |
194 | cred_pos = uri.find(':') |
|
194 | cred_pos = uri.find(':') | |
195 | if cred_pos == -1: |
|
195 | if cred_pos == -1: | |
196 | host, port = uri, None |
|
196 | host, port = uri, None | |
197 | else: |
|
197 | else: | |
198 | host, port = uri[:cred_pos], uri[cred_pos + 1:] |
|
198 | host, port = uri[:cred_pos], uri[cred_pos + 1:] | |
199 |
|
199 | |||
200 | return [_f for _f in [proto, host, port] if _f] |
|
200 | return [_f for _f in [proto, host, port] if _f] | |
201 |
|
201 | |||
202 |
|
202 | |||
203 | def credentials_filter(uri): |
|
203 | def credentials_filter(uri): | |
204 | """ |
|
204 | """ | |
205 | Returns a url with removed credentials |
|
205 | Returns a url with removed credentials | |
206 |
|
206 | |||
207 | :param uri: |
|
207 | :param uri: | |
208 | """ |
|
208 | """ | |
209 |
|
209 | |||
210 | uri = uri_filter(uri) |
|
210 | uri = uri_filter(uri) | |
211 | # check if we have port |
|
211 | # check if we have port | |
212 | if len(uri) > 2 and uri[2]: |
|
212 | if len(uri) > 2 and uri[2]: | |
213 | uri[2] = ':' + uri[2] |
|
213 | uri[2] = ':' + uri[2] | |
214 |
|
214 | |||
215 | return ''.join(uri) |
|
215 | return ''.join(uri) | |
216 |
|
216 | |||
217 |
|
217 | |||
218 | def get_clone_url(clone_uri_tmpl, prefix_url, repo_name, repo_id, username=None): |
|
218 | def get_clone_url(clone_uri_tmpl, prefix_url, repo_name, repo_id, username=None): | |
219 | parsed_url = urlobject.URLObject(prefix_url) |
|
219 | parsed_url = urlobject.URLObject(prefix_url) | |
220 | prefix = urllib.parse.unquote(parsed_url.path.rstrip('/')) |
|
220 | prefix = urllib.parse.unquote(parsed_url.path.rstrip('/')) | |
221 | try: |
|
221 | try: | |
222 | system_user = pwd.getpwuid(os.getuid()).pw_name |
|
222 | system_user = pwd.getpwuid(os.getuid()).pw_name | |
223 | except NameError: # TODO: support all systems - especially Windows |
|
223 | except NameError: # TODO: support all systems - especially Windows | |
224 | system_user = 'kallithea' # hardcoded default value ... |
|
224 | system_user = 'kallithea' # hardcoded default value ... | |
225 | args = { |
|
225 | args = { | |
226 | 'scheme': parsed_url.scheme, |
|
226 | 'scheme': parsed_url.scheme, | |
227 | 'user': urllib.parse.quote(username or ''), |
|
227 | 'user': urllib.parse.quote(username or ''), | |
228 | 'netloc': parsed_url.netloc + prefix, # like "hostname:port/prefix" (with optional ":port" and "/prefix") |
|
228 | 'netloc': parsed_url.netloc + prefix, # like "hostname:port/prefix" (with optional ":port" and "/prefix") | |
229 | 'prefix': prefix, # undocumented, empty or starting with / |
|
229 | 'prefix': prefix, # undocumented, empty or starting with / | |
230 | 'repo': repo_name, |
|
230 | 'repo': repo_name, | |
231 | 'repoid': str(repo_id), |
|
231 | 'repoid': str(repo_id), | |
232 | 'system_user': system_user, |
|
232 | 'system_user': system_user, | |
233 | 'hostname': parsed_url.hostname, |
|
233 | 'hostname': parsed_url.hostname, | |
234 | } |
|
234 | } | |
235 | url = re.sub('{([^{}]+)}', lambda m: args.get(m.group(1), m.group(0)), clone_uri_tmpl) |
|
235 | url = re.sub('{([^{}]+)}', lambda m: args.get(m.group(1), m.group(0)), clone_uri_tmpl) | |
236 |
|
236 | |||
237 | # remove leading @ sign if it's present. Case of empty user |
|
237 | # remove leading @ sign if it's present. Case of empty user | |
238 | url_obj = urlobject.URLObject(url) |
|
238 | url_obj = urlobject.URLObject(url) | |
239 | if not url_obj.username: |
|
239 | if not url_obj.username: | |
240 | url_obj = url_obj.with_username(None) |
|
240 | url_obj = url_obj.with_username(None) | |
241 |
|
241 | |||
242 | return str(url_obj) |
|
242 | return str(url_obj) | |
243 |
|
243 | |||
244 |
|
244 | |||
245 | def short_ref_name(ref_type, ref_name): |
|
245 | def short_ref_name(ref_type, ref_name): | |
246 | """Return short description of PR ref - revs will be truncated""" |
|
246 | """Return short description of PR ref - revs will be truncated""" | |
247 | if ref_type == 'rev': |
|
247 | if ref_type == 'rev': | |
248 | return ref_name[:12] |
|
248 | return ref_name[:12] | |
249 | return ref_name |
|
249 | return ref_name | |
250 |
|
250 | |||
251 |
|
251 | |||
252 | def link_to_ref(repo_name, ref_type, ref_name, rev=None): |
|
252 | def link_to_ref(repo_name, ref_type, ref_name, rev=None): | |
253 | """ |
|
253 | """ | |
254 | Return full markup for a PR ref to changeset_home for a changeset. |
|
254 | Return full markup for a PR ref to changeset_home for a changeset. | |
255 | If ref_type is 'branch', it will link to changelog. |
|
255 | If ref_type is 'branch', it will link to changelog. | |
256 | ref_name is shortened if ref_type is 'rev'. |
|
256 | ref_name is shortened if ref_type is 'rev'. | |
257 | if rev is specified, show it too, explicitly linking to that revision. |
|
257 | if rev is specified, show it too, explicitly linking to that revision. | |
258 | """ |
|
258 | """ | |
259 | txt = short_ref_name(ref_type, ref_name) |
|
259 | txt = short_ref_name(ref_type, ref_name) | |
260 | if ref_type == 'branch': |
|
260 | if ref_type == 'branch': | |
261 | u = webutils.url('changelog_home', repo_name=repo_name, branch=ref_name) |
|
261 | u = webutils.url('changelog_home', repo_name=repo_name, branch=ref_name) | |
262 | else: |
|
262 | else: | |
263 | u = webutils.url('changeset_home', repo_name=repo_name, revision=ref_name) |
|
263 | u = webutils.url('changeset_home', repo_name=repo_name, revision=ref_name) | |
264 | l = webutils.link_to(repo_name + '#' + txt, u) |
|
264 | l = webutils.link_to(repo_name + '#' + txt, u) | |
265 | if rev and ref_type != 'rev': |
|
265 | if rev and ref_type != 'rev': | |
266 | l = webutils.literal('%s (%s)' % (l, webutils.link_to(rev[:12], webutils.url('changeset_home', repo_name=repo_name, revision=rev)))) |
|
266 | l = webutils.literal('%s (%s)' % (l, webutils.link_to(rev[:12], webutils.url('changeset_home', repo_name=repo_name, revision=rev)))) | |
267 | return l |
|
267 | return l | |
268 |
|
268 | |||
269 |
|
269 | |||
270 | def get_changeset_safe(repo, rev): |
|
270 | def get_changeset_safe(repo, rev): | |
271 | """ |
|
271 | """ | |
272 | Safe version of get_changeset if this changeset doesn't exists for a |
|
272 | Safe version of get_changeset if this changeset doesn't exists for a | |
273 | repo it returns a Dummy one instead |
|
273 | repo it returns a Dummy one instead | |
274 |
|
274 | |||
275 | :param repo: |
|
275 | :param repo: | |
276 | :param rev: |
|
276 | :param rev: | |
277 | """ |
|
277 | """ | |
278 | if not isinstance(repo, BaseRepository): |
|
278 | if not isinstance(repo, BaseRepository): | |
279 | raise Exception('You must pass an Repository ' |
|
279 | raise Exception('You must pass an Repository ' | |
280 | 'object as first argument got %s' % type(repo)) |
|
280 | 'object as first argument got %s' % type(repo)) | |
281 |
|
281 | |||
282 | try: |
|
282 | try: | |
283 | cs = repo.get_changeset(rev) |
|
283 | cs = repo.get_changeset(rev) | |
284 | except (RepositoryError, LookupError): |
|
284 | except (RepositoryError, LookupError): | |
285 | cs = EmptyChangeset(requested_revision=rev) |
|
285 | cs = EmptyChangeset(requested_revision=rev) | |
286 | return cs |
|
286 | return cs | |
287 |
|
287 | |||
288 |
|
288 | |||
289 | def datetime_to_time(dt): |
|
289 | def datetime_to_time(dt): | |
290 | if dt: |
|
290 | if dt: | |
291 | return time.mktime(dt.timetuple()) |
|
291 | return time.mktime(dt.timetuple()) | |
292 |
|
292 | |||
293 |
|
293 | |||
294 | def time_to_datetime(tm): |
|
294 | def time_to_datetime(tm): | |
295 | if tm: |
|
295 | if tm: | |
296 | if isinstance(tm, str): |
|
296 | if isinstance(tm, str): | |
297 | try: |
|
297 | try: | |
298 | tm = float(tm) |
|
298 | tm = float(tm) | |
299 | except ValueError: |
|
299 | except ValueError: | |
300 | return |
|
300 | return | |
301 | return datetime.datetime.fromtimestamp(tm) |
|
301 | return datetime.datetime.fromtimestamp(tm) | |
302 |
|
302 | |||
303 |
|
303 | |||
304 | class AttributeDict(dict): |
|
304 | class AttributeDict(dict): | |
305 | def __getattr__(self, attr): |
|
305 | def __getattr__(self, attr): | |
306 | return self.get(attr, None) |
|
306 | return self.get(attr, None) | |
307 | __setattr__ = dict.__setitem__ |
|
307 | __setattr__ = dict.__setitem__ | |
308 | __delattr__ = dict.__delitem__ |
|
308 | __delattr__ = dict.__delitem__ | |
309 |
|
309 | |||
310 |
|
310 | |||
311 | def obfuscate_url_pw(engine): |
|
311 | def obfuscate_url_pw(engine): | |
312 | try: |
|
312 | try: | |
313 | _url = sa_url.make_url(engine or '') |
|
313 | _url = sa_url.make_url(engine or '') | |
314 | except ArgumentError: |
|
314 | except ArgumentError: | |
315 | return engine |
|
315 | return engine | |
316 | if _url.password: |
|
316 | if _url.password: | |
317 | _url.password = 'XXXXX' |
|
317 | _url.password = 'XXXXX' | |
318 | return str(_url) |
|
318 | return str(_url) | |
319 |
|
319 | |||
320 |
|
320 | |||
321 | class HookEnvironmentError(Exception): pass |
|
321 | class HookEnvironmentError(Exception): pass | |
322 |
|
322 | |||
323 |
|
323 | |||
324 | def get_hook_environment(): |
|
324 | def get_hook_environment(): | |
325 | """ |
|
325 | """ | |
326 | Get hook context by deserializing the global KALLITHEA_EXTRAS environment |
|
326 | Get hook context by deserializing the global KALLITHEA_EXTRAS environment | |
327 | variable. |
|
327 | variable. | |
328 |
|
328 | |||
329 | Called early in Git out-of-process hooks to get .ini config path so the |
|
329 | Called early in Git out-of-process hooks to get .ini config path so the | |
330 | basic environment can be configured properly. Also used in all hooks to get |
|
330 | basic environment can be configured properly. Also used in all hooks to get | |
331 | information about the action that triggered it. |
|
331 | information about the action that triggered it. | |
332 | """ |
|
332 | """ | |
333 |
|
333 | |||
334 | try: |
|
334 | try: | |
335 | kallithea_extras = os.environ['KALLITHEA_EXTRAS'] |
|
335 | kallithea_extras = os.environ['KALLITHEA_EXTRAS'] | |
336 | except KeyError: |
|
336 | except KeyError: | |
337 | raise HookEnvironmentError("Environment variable KALLITHEA_EXTRAS not found") |
|
337 | raise HookEnvironmentError("Environment variable KALLITHEA_EXTRAS not found") | |
338 |
|
338 | |||
339 | extras = json.loads(kallithea_extras) |
|
339 | extras = json.loads(kallithea_extras) | |
340 | for k in ['username', 'repository', 'scm', 'action', 'ip', 'config']: |
|
340 | for k in ['username', 'repository', 'scm', 'action', 'ip', 'config']: | |
341 | try: |
|
341 | try: | |
342 | extras[k] |
|
342 | extras[k] | |
343 | except KeyError: |
|
343 | except KeyError: | |
344 | raise HookEnvironmentError('Missing key %s in KALLITHEA_EXTRAS %s' % (k, extras)) |
|
344 | raise HookEnvironmentError('Missing key %s in KALLITHEA_EXTRAS %s' % (k, extras)) | |
345 |
|
345 | |||
346 | return AttributeDict(extras) |
|
346 | return AttributeDict(extras) | |
347 |
|
347 | |||
348 |
|
348 | |||
349 | def set_hook_environment(username, ip_addr, repo_name, repo_alias, action=None): |
|
349 | def set_hook_environment(username, ip_addr, repo_name, repo_alias, action=None): | |
350 | """Prepare global context for running hooks by serializing data in the |
|
350 | """Prepare global context for running hooks by serializing data in the | |
351 | global KALLITHEA_EXTRAS environment variable. |
|
351 | global KALLITHEA_EXTRAS environment variable. | |
352 |
|
352 | |||
353 | Most importantly, this allow Git hooks to do proper logging and updating of |
|
353 | Most importantly, this allow Git hooks to do proper logging and updating of | |
354 | caches after pushes. |
|
354 | caches after pushes. | |
355 |
|
355 | |||
356 | Must always be called before anything with hooks are invoked. |
|
356 | Must always be called before anything with hooks are invoked. | |
357 | """ |
|
357 | """ | |
358 | extras = { |
|
358 | extras = { | |
359 | 'ip': ip_addr, # used in action_logger |
|
359 | 'ip': ip_addr, # used in action_logger | |
360 | 'username': username, |
|
360 | 'username': username, | |
361 | 'action': action or 'push_local', # used in process_pushed_raw_ids action_logger |
|
361 | 'action': action or 'push_local', # used in process_pushed_raw_ids action_logger | |
362 | 'repository': repo_name, |
|
362 | 'repository': repo_name, | |
363 | 'scm': repo_alias, |
|
363 | 'scm': repo_alias, | |
364 | 'config': kallithea.CONFIG['__file__'], # used by git hook to read config |
|
364 | 'config': kallithea.CONFIG['__file__'], # used by git hook to read config | |
365 | } |
|
365 | } | |
366 | os.environ['KALLITHEA_EXTRAS'] = json.dumps(extras) |
|
366 | os.environ['KALLITHEA_EXTRAS'] = json.dumps(extras) | |
367 |
|
367 | |||
368 |
|
368 | |||
369 | def get_current_authuser(): |
|
369 | def get_current_authuser(): | |
370 | """ |
|
370 | """ | |
371 | Gets kallithea user from threadlocal tmpl_context variable if it's |
|
371 | Gets kallithea user from threadlocal tmpl_context variable if it's | |
372 | defined, else returns None. |
|
372 | defined, else returns None. | |
373 | """ |
|
373 | """ | |
374 | try: |
|
374 | try: | |
375 | return getattr(tmpl_context, 'authuser', None) |
|
375 | return getattr(tmpl_context, 'authuser', None) | |
376 | except TypeError: # No object (name: context) has been registered for this thread |
|
376 | except TypeError: # No object (name: context) has been registered for this thread | |
377 | return None |
|
377 | return None | |
378 |
|
378 | |||
379 |
|
379 | |||
380 | def urlreadable(s, _cleanstringsub=re.compile('[^-a-zA-Z0-9./]+').sub): |
|
380 | def urlreadable(s, _cleanstringsub=re.compile('[^-a-zA-Z0-9./]+').sub): | |
381 | return _cleanstringsub('_', s).rstrip('_') |
|
381 | return _cleanstringsub('_', s).rstrip('_') | |
382 |
|
382 | |||
383 |
|
383 | |||
384 | def recursive_replace(str_, replace=' '): |
|
384 | def recursive_replace(str_, replace=' '): | |
385 | """ |
|
385 | """ | |
386 | Recursive replace of given sign to just one instance |
|
386 | Recursive replace of given sign to just one instance | |
387 |
|
387 | |||
388 | :param str_: given string |
|
388 | :param str_: given string | |
389 | :param replace: char to find and replace multiple instances |
|
389 | :param replace: char to find and replace multiple instances | |
390 |
|
390 | |||
391 | Examples:: |
|
391 | Examples:: | |
392 | >>> recursive_replace("Mighty---Mighty-Bo--sstones",'-') |
|
392 | >>> recursive_replace("Mighty---Mighty-Bo--sstones",'-') | |
393 | 'Mighty-Mighty-Bo-sstones' |
|
393 | 'Mighty-Mighty-Bo-sstones' | |
394 | """ |
|
394 | """ | |
395 |
|
395 | |||
396 | if str_.find(replace * 2) == -1: |
|
396 | if str_.find(replace * 2) == -1: | |
397 | return str_ |
|
397 | return str_ | |
398 | else: |
|
398 | else: | |
399 | str_ = str_.replace(replace * 2, replace) |
|
399 | str_ = str_.replace(replace * 2, replace) | |
400 | return recursive_replace(str_, replace) |
|
400 | return recursive_replace(str_, replace) | |
401 |
|
401 | |||
402 |
|
402 | |||
403 | def repo_name_slug(value): |
|
403 | def repo_name_slug(value): | |
404 | """ |
|
404 | """ | |
405 | Return slug of name of repository |
|
405 | Return slug of name of repository | |
406 | This function is called on each creation/modification |
|
406 | This function is called on each creation/modification | |
407 | of repository to prevent bad names in repo |
|
407 | of repository to prevent bad names in repo | |
408 | """ |
|
408 | """ | |
409 |
|
409 | |||
410 | slug = remove_formatting(value) |
|
410 | slug = remove_formatting(value) | |
411 | slug = strip_tags(slug) |
|
411 | slug = strip_tags(slug) | |
412 |
|
412 | |||
413 | for c in r"""`?=[]\;'"<>,/~!@#$%^&*()+{}|: """: |
|
413 | for c in r"""`?=[]\;'"<>,/~!@#$%^&*()+{}|: """: | |
414 | slug = slug.replace(c, '-') |
|
414 | slug = slug.replace(c, '-') | |
415 | slug = recursive_replace(slug, '-') |
|
415 | slug = recursive_replace(slug, '-') | |
416 | slug = collapse(slug, '-') |
|
416 | slug = collapse(slug, '-') | |
417 | return slug |
|
417 | return slug | |
418 |
|
418 | |||
419 |
|
419 | |||
420 | def ask_ok(prompt, retries=4, complaint='Yes or no please!'): |
|
420 | def ask_ok(prompt, retries=4, complaint='Yes or no please!'): | |
421 | while True: |
|
421 | while True: | |
422 | ok = input(prompt) |
|
422 | ok = input(prompt) | |
423 | if ok in ('y', 'ye', 'yes'): |
|
423 | if ok in ('y', 'ye', 'yes'): | |
424 | return True |
|
424 | return True | |
425 | if ok in ('n', 'no', 'nop', 'nope'): |
|
425 | if ok in ('n', 'no', 'nop', 'nope'): | |
426 | return False |
|
426 | return False | |
427 | retries = retries - 1 |
|
427 | retries = retries - 1 | |
428 | if retries < 0: |
|
428 | if retries < 0: | |
429 | raise IOError |
|
429 | raise IOError | |
430 | print(complaint) |
|
430 | print(complaint) | |
431 |
|
431 | |||
432 |
|
432 | |||
433 | class PasswordGenerator(object): |
|
433 | class PasswordGenerator(object): | |
434 | """ |
|
434 | """ | |
435 | This is a simple class for generating password from different sets of |
|
435 | This is a simple class for generating password from different sets of | |
436 | characters |
|
436 | characters | |
437 | usage:: |
|
437 | usage:: | |
438 |
|
438 | |||
439 | passwd_gen = PasswordGenerator() |
|
439 | passwd_gen = PasswordGenerator() | |
440 | #print 8-letter password containing only big and small letters |
|
440 | #print 8-letter password containing only big and small letters | |
441 | of alphabet |
|
441 | of alphabet | |
442 | passwd_gen.gen_password(8, passwd_gen.ALPHABETS_BIG_SMALL) |
|
442 | passwd_gen.gen_password(8, passwd_gen.ALPHABETS_BIG_SMALL) | |
443 | """ |
|
443 | """ | |
444 | ALPHABETS_NUM = r'''1234567890''' |
|
444 | ALPHABETS_NUM = r'''1234567890''' | |
445 | ALPHABETS_SMALL = r'''qwertyuiopasdfghjklzxcvbnm''' |
|
445 | ALPHABETS_SMALL = r'''qwertyuiopasdfghjklzxcvbnm''' | |
446 | ALPHABETS_BIG = r'''QWERTYUIOPASDFGHJKLZXCVBNM''' |
|
446 | ALPHABETS_BIG = r'''QWERTYUIOPASDFGHJKLZXCVBNM''' | |
447 | ALPHABETS_SPECIAL = r'''`-=[]\;',./~!@#$%^&*()_+{}|:"<>?''' |
|
447 | ALPHABETS_SPECIAL = r'''`-=[]\;',./~!@#$%^&*()_+{}|:"<>?''' | |
448 | ALPHABETS_FULL = ALPHABETS_BIG + ALPHABETS_SMALL \ |
|
448 | ALPHABETS_FULL = ALPHABETS_BIG + ALPHABETS_SMALL \ | |
449 | + ALPHABETS_NUM + ALPHABETS_SPECIAL |
|
449 | + ALPHABETS_NUM + ALPHABETS_SPECIAL | |
450 | ALPHABETS_ALPHANUM = ALPHABETS_BIG + ALPHABETS_SMALL + ALPHABETS_NUM |
|
450 | ALPHABETS_ALPHANUM = ALPHABETS_BIG + ALPHABETS_SMALL + ALPHABETS_NUM | |
451 | ALPHABETS_BIG_SMALL = ALPHABETS_BIG + ALPHABETS_SMALL |
|
451 | ALPHABETS_BIG_SMALL = ALPHABETS_BIG + ALPHABETS_SMALL | |
452 | ALPHABETS_ALPHANUM_BIG = ALPHABETS_BIG + ALPHABETS_NUM |
|
452 | ALPHABETS_ALPHANUM_BIG = ALPHABETS_BIG + ALPHABETS_NUM | |
453 | ALPHABETS_ALPHANUM_SMALL = ALPHABETS_SMALL + ALPHABETS_NUM |
|
453 | ALPHABETS_ALPHANUM_SMALL = ALPHABETS_SMALL + ALPHABETS_NUM | |
454 |
|
454 | |||
455 | def gen_password(self, length, alphabet=ALPHABETS_FULL): |
|
455 | def gen_password(self, length, alphabet=ALPHABETS_FULL): | |
456 | assert len(alphabet) <= 256, alphabet |
|
456 | assert len(alphabet) <= 256, alphabet | |
457 | l = [] |
|
457 | l = [] | |
458 | while len(l) < length: |
|
458 | while len(l) < length: | |
459 | i = ord(os.urandom(1)) |
|
459 | i = ord(os.urandom(1)) | |
460 | if i < len(alphabet): |
|
460 | if i < len(alphabet): | |
461 | l.append(alphabet[i]) |
|
461 | l.append(alphabet[i]) | |
462 | return ''.join(l) |
|
462 | return ''.join(l) | |
463 |
|
463 | |||
464 |
|
464 | |||
465 | def get_crypt_password(password): |
|
465 | def get_crypt_password(password): | |
466 | """ |
|
466 | """ | |
467 | Cryptographic function used for bcrypt password hashing. |
|
467 | Cryptographic function used for bcrypt password hashing. | |
468 |
|
468 | |||
469 | :param password: password to hash |
|
469 | :param password: password to hash | |
470 | """ |
|
470 | """ | |
471 | return ascii_str(bcrypt.hashpw(safe_bytes(password), bcrypt.gensalt(10))) |
|
471 | return ascii_str(bcrypt.hashpw(safe_bytes(password), bcrypt.gensalt(10))) | |
472 |
|
472 | |||
473 |
|
473 | |||
474 | def check_password(password, hashed): |
|
474 | def check_password(password, hashed): | |
475 | """ |
|
475 | """ | |
476 | Checks password match the hashed value using bcrypt. |
|
476 | Checks password match the hashed value using bcrypt. | |
477 | Remains backwards compatible and accept plain sha256 hashes which used to |
|
477 | Remains backwards compatible and accept plain sha256 hashes which used to | |
478 | be used on Windows. |
|
478 | be used on Windows. | |
479 |
|
479 | |||
480 | :param password: password |
|
480 | :param password: password | |
481 | :param hashed: password in hashed form |
|
481 | :param hashed: password in hashed form | |
482 | """ |
|
482 | """ | |
483 | # sha256 hashes will always be 64 hex chars |
|
483 | # sha256 hashes will always be 64 hex chars | |
484 | # bcrypt hashes will always contain $ (and be shorter) |
|
484 | # bcrypt hashes will always contain $ (and be shorter) | |
485 | if len(hashed) == 64 and all(x in string.hexdigits for x in hashed): |
|
485 | if len(hashed) == 64 and all(x in string.hexdigits for x in hashed): | |
486 | return hashlib.sha256(password).hexdigest() == hashed |
|
486 | return hashlib.sha256(password).hexdigest() == hashed | |
487 | try: |
|
487 | try: | |
488 | return bcrypt.checkpw(safe_bytes(password), ascii_bytes(hashed)) |
|
488 | return bcrypt.checkpw(safe_bytes(password), ascii_bytes(hashed)) | |
489 | except ValueError as e: |
|
489 | except ValueError as e: | |
490 | # bcrypt will throw ValueError 'Invalid hashed_password salt' on all password errors |
|
490 | # bcrypt will throw ValueError 'Invalid hashed_password salt' on all password errors | |
491 | log.error('error from bcrypt checking password: %s', e) |
|
491 | log.error('error from bcrypt checking password: %s', e) | |
492 | return False |
|
492 | return False | |
493 | log.error('check_password failed - no method found for hash length %s', len(hashed)) |
|
493 | log.error('check_password failed - no method found for hash length %s', len(hashed)) | |
494 | return False |
|
494 | return False | |
495 |
|
495 | |||
496 |
|
496 | |||
497 |
git_req_ver = |
|
497 | git_req_ver = Version('1.7.4') | |
498 |
|
498 | |||
499 | def check_git_version(): |
|
499 | def check_git_version(): | |
500 | """ |
|
500 | """ | |
501 | Checks what version of git is installed on the system, and raise a system exit |
|
501 | Checks what version of git is installed on the system, and raise a system exit | |
502 | if it's too old for Kallithea to work properly. |
|
502 | if it's too old for Kallithea to work properly. | |
503 | """ |
|
503 | """ | |
504 | if 'git' not in kallithea.BACKENDS: |
|
504 | if 'git' not in kallithea.BACKENDS: | |
505 | return None |
|
505 | return None | |
506 |
|
506 | |||
507 | if not settings.GIT_EXECUTABLE_PATH: |
|
507 | if not settings.GIT_EXECUTABLE_PATH: | |
508 | log.warning('No git executable configured - check "git_path" in the ini file.') |
|
508 | log.warning('No git executable configured - check "git_path" in the ini file.') | |
509 | return None |
|
509 | return None | |
510 |
|
510 | |||
511 | try: |
|
511 | try: | |
512 | stdout, stderr = GitRepository._run_git_command(['--version']) |
|
512 | stdout, stderr = GitRepository._run_git_command(['--version']) | |
513 | except RepositoryError as e: |
|
513 | except RepositoryError as e: | |
514 | # message will already have been logged as error |
|
514 | # message will already have been logged as error | |
515 | log.warning('No working git executable found - check "git_path" in the ini file.') |
|
515 | log.warning('No working git executable found - check "git_path" in the ini file.') | |
516 | return None |
|
516 | return None | |
517 |
|
517 | |||
518 | if stderr: |
|
518 | if stderr: | |
519 | log.warning('Error/stderr from "%s --version":\n%s', settings.GIT_EXECUTABLE_PATH, safe_str(stderr)) |
|
519 | log.warning('Error/stderr from "%s --version":\n%s', settings.GIT_EXECUTABLE_PATH, safe_str(stderr)) | |
520 |
|
520 | |||
521 | if not stdout: |
|
521 | if not stdout: | |
522 | log.warning('No working git executable found - check "git_path" in the ini file.') |
|
522 | log.warning('No working git executable found - check "git_path" in the ini file.') | |
523 | return None |
|
523 | return None | |
524 |
|
524 | |||
525 | output = safe_str(stdout).strip() |
|
525 | output = safe_str(stdout).strip() | |
526 | m = re.search(r"\d+.\d+.\d+", output) |
|
526 | m = re.search(r"\d+.\d+.\d+", output) | |
527 | if m: |
|
527 | if m: | |
528 |
ver = |
|
528 | ver = Version(m.group(0)) | |
529 | log.debug('Git executable: "%s", version %s (parsed from: "%s")', |
|
529 | log.debug('Git executable: "%s", version %s (parsed from: "%s")', | |
530 | settings.GIT_EXECUTABLE_PATH, ver, output) |
|
530 | settings.GIT_EXECUTABLE_PATH, ver, output) | |
531 | if ver < git_req_ver: |
|
531 | if ver < git_req_ver: | |
532 | log.error('Kallithea detected %s version %s, which is too old ' |
|
532 | log.error('Kallithea detected %s version %s, which is too old ' | |
533 | 'for the system to function properly. ' |
|
533 | 'for the system to function properly. ' | |
534 | 'Please upgrade to version %s or later. ' |
|
534 | 'Please upgrade to version %s or later. ' | |
535 | 'If you strictly need Mercurial repositories, you can ' |
|
535 | 'If you strictly need Mercurial repositories, you can ' | |
536 | 'clear the "git_path" setting in the ini file.', |
|
536 | 'clear the "git_path" setting in the ini file.', | |
537 | settings.GIT_EXECUTABLE_PATH, ver, git_req_ver) |
|
537 | settings.GIT_EXECUTABLE_PATH, ver, git_req_ver) | |
538 | log.error("Terminating ...") |
|
538 | log.error("Terminating ...") | |
539 | sys.exit(1) |
|
539 | sys.exit(1) | |
540 | else: |
|
540 | else: | |
541 |
ver = |
|
541 | ver = Version('0.0.0') | |
542 | log.warning('Error finding version number in "%s --version" stdout:\n%s', |
|
542 | log.warning('Error finding version number in "%s --version" stdout:\n%s', | |
543 | settings.GIT_EXECUTABLE_PATH, output) |
|
543 | settings.GIT_EXECUTABLE_PATH, output) | |
544 |
|
544 | |||
545 | return ver |
|
545 | return ver |
@@ -1,293 +1,294 b'' | |||||
1 | #!/usr/bin/env python3 |
|
1 | #!/usr/bin/env python3 | |
2 |
|
2 | |||
3 |
|
3 | |||
4 | import re |
|
4 | import re | |
5 | import sys |
|
5 | import sys | |
6 |
|
6 | |||
7 |
|
7 | |||
8 | ignored_modules = set(''' |
|
8 | ignored_modules = set(''' | |
9 | argparse |
|
9 | argparse | |
10 | base64 |
|
10 | base64 | |
11 | bcrypt |
|
11 | bcrypt | |
12 | binascii |
|
12 | binascii | |
13 | bleach |
|
13 | bleach | |
14 | calendar |
|
14 | calendar | |
15 | celery |
|
15 | celery | |
16 | celery |
|
16 | celery | |
17 | chardet |
|
17 | chardet | |
18 | click |
|
18 | click | |
19 | collections |
|
19 | collections | |
20 | configparser |
|
20 | configparser | |
21 | copy |
|
21 | copy | |
22 | csv |
|
22 | csv | |
23 | ctypes |
|
23 | ctypes | |
24 | datetime |
|
24 | datetime | |
25 | dateutil |
|
25 | dateutil | |
26 | decimal |
|
26 | decimal | |
27 | decorator |
|
27 | decorator | |
28 | difflib |
|
28 | difflib | |
29 | distutils |
|
29 | distutils | |
30 | docutils |
|
30 | docutils | |
31 |
|
31 | |||
32 | errno |
|
32 | errno | |
33 | fileinput |
|
33 | fileinput | |
34 | functools |
|
34 | functools | |
35 | getpass |
|
35 | getpass | |
36 | grp |
|
36 | grp | |
37 | hashlib |
|
37 | hashlib | |
38 | hmac |
|
38 | hmac | |
39 | html |
|
39 | html | |
40 | http |
|
40 | http | |
41 | imp |
|
41 | imp | |
42 | importlib |
|
42 | importlib | |
43 | inspect |
|
43 | inspect | |
44 | io |
|
44 | io | |
45 | ipaddr |
|
45 | ipaddr | |
46 | IPython |
|
46 | IPython | |
47 | isapi_wsgi |
|
47 | isapi_wsgi | |
48 | itertools |
|
48 | itertools | |
49 | json |
|
49 | json | |
50 | kajiki |
|
50 | kajiki | |
51 | ldap |
|
51 | ldap | |
52 | logging |
|
52 | logging | |
53 | mako |
|
53 | mako | |
54 | markdown |
|
54 | markdown | |
55 | mimetypes |
|
55 | mimetypes | |
56 | mock |
|
56 | mock | |
57 | msvcrt |
|
57 | msvcrt | |
58 | multiprocessing |
|
58 | multiprocessing | |
59 | operator |
|
59 | operator | |
60 | os |
|
60 | os | |
61 | paginate |
|
61 | paginate | |
62 | paginate_sqlalchemy |
|
62 | paginate_sqlalchemy | |
63 | pam |
|
63 | pam | |
64 | paste |
|
64 | paste | |
65 | pkg_resources |
|
65 | pkg_resources | |
66 | platform |
|
66 | platform | |
67 | posixpath |
|
67 | posixpath | |
68 | pprint |
|
68 | pprint | |
69 | pwd |
|
69 | pwd | |
70 | pyflakes |
|
70 | pyflakes | |
71 | pytest |
|
71 | pytest | |
72 | pytest_localserver |
|
72 | pytest_localserver | |
73 | random |
|
73 | random | |
74 | re |
|
74 | re | |
75 | routes |
|
75 | routes | |
76 | setuptools |
|
76 | setuptools | |
77 | shlex |
|
77 | shlex | |
78 | shutil |
|
78 | shutil | |
79 | smtplib |
|
79 | smtplib | |
80 | socket |
|
80 | socket | |
81 | ssl |
|
81 | ssl | |
82 | stat |
|
82 | stat | |
83 | string |
|
83 | string | |
84 | struct |
|
84 | struct | |
85 | subprocess |
|
85 | subprocess | |
86 | sys |
|
86 | sys | |
87 | tarfile |
|
87 | tarfile | |
88 | tempfile |
|
88 | tempfile | |
89 | textwrap |
|
89 | textwrap | |
90 | tgext |
|
90 | tgext | |
91 | threading |
|
91 | threading | |
92 | time |
|
92 | time | |
93 | traceback |
|
93 | traceback | |
94 | traitlets |
|
94 | traitlets | |
95 | types |
|
95 | types | |
96 | typing |
|
96 | typing | |
97 | urllib |
|
97 | urllib | |
98 | urlobject |
|
98 | urlobject | |
99 | uuid |
|
99 | uuid | |
100 | warnings |
|
100 | warnings | |
101 | webhelpers2 |
|
101 | webhelpers2 | |
102 | webob |
|
102 | webob | |
103 | webtest |
|
103 | webtest | |
104 | whoosh |
|
104 | whoosh | |
105 | win32traceutil |
|
105 | win32traceutil | |
106 | zipfile |
|
106 | zipfile | |
107 | '''.split()) |
|
107 | '''.split()) | |
108 |
|
108 | |||
109 | top_modules = set(''' |
|
109 | top_modules = set(''' | |
110 | kallithea.alembic |
|
110 | kallithea.alembic | |
111 | kallithea.bin |
|
111 | kallithea.bin | |
112 | kallithea.config |
|
112 | kallithea.config | |
113 | kallithea.controllers |
|
113 | kallithea.controllers | |
114 | kallithea.templates.py |
|
114 | kallithea.templates.py | |
115 | scripts |
|
115 | scripts | |
116 | '''.split()) |
|
116 | '''.split()) | |
117 |
|
117 | |||
118 | bottom_external_modules = set(''' |
|
118 | bottom_external_modules = set(''' | |
119 | tg |
|
119 | tg | |
120 | mercurial |
|
120 | mercurial | |
121 | sqlalchemy |
|
121 | sqlalchemy | |
122 | alembic |
|
122 | alembic | |
123 | formencode |
|
123 | formencode | |
124 | pygments |
|
124 | pygments | |
125 | dulwich |
|
125 | dulwich | |
126 | beaker |
|
126 | beaker | |
127 | psycopg2 |
|
127 | psycopg2 | |
128 | docs |
|
128 | docs | |
129 | setup |
|
129 | setup | |
130 | conftest |
|
130 | conftest | |
|
131 | packaging | |||
131 | '''.split()) |
|
132 | '''.split()) | |
132 |
|
133 | |||
133 | normal_modules = set(''' |
|
134 | normal_modules = set(''' | |
134 | kallithea |
|
135 | kallithea | |
135 | kallithea.controllers.base |
|
136 | kallithea.controllers.base | |
136 | kallithea.lib |
|
137 | kallithea.lib | |
137 | kallithea.lib.auth |
|
138 | kallithea.lib.auth | |
138 | kallithea.lib.auth_modules |
|
139 | kallithea.lib.auth_modules | |
139 | kallithea.lib.celerylib |
|
140 | kallithea.lib.celerylib | |
140 | kallithea.lib.db_manage |
|
141 | kallithea.lib.db_manage | |
141 | kallithea.lib.helpers |
|
142 | kallithea.lib.helpers | |
142 | kallithea.lib.hooks |
|
143 | kallithea.lib.hooks | |
143 | kallithea.lib.indexers |
|
144 | kallithea.lib.indexers | |
144 | kallithea.lib.utils |
|
145 | kallithea.lib.utils | |
145 | kallithea.lib.utils2 |
|
146 | kallithea.lib.utils2 | |
146 | kallithea.lib.vcs |
|
147 | kallithea.lib.vcs | |
147 | kallithea.lib.webutils |
|
148 | kallithea.lib.webutils | |
148 | kallithea.model |
|
149 | kallithea.model | |
149 | kallithea.model.async_tasks |
|
150 | kallithea.model.async_tasks | |
150 | kallithea.model.scm |
|
151 | kallithea.model.scm | |
151 | kallithea.templates.py |
|
152 | kallithea.templates.py | |
152 | '''.split()) |
|
153 | '''.split()) | |
153 |
|
154 | |||
154 | shown_modules = normal_modules | top_modules |
|
155 | shown_modules = normal_modules | top_modules | |
155 |
|
156 | |||
156 | # break the chains somehow - this is a cleanup TODO list |
|
157 | # break the chains somehow - this is a cleanup TODO list | |
157 | known_violations = set([ |
|
158 | known_violations = set([ | |
158 | ('kallithea.lib.auth_modules', 'kallithea.lib.auth'), # needs base&facade |
|
159 | ('kallithea.lib.auth_modules', 'kallithea.lib.auth'), # needs base&facade | |
159 | ('kallithea.lib.utils', 'kallithea.model'), # clean up utils |
|
160 | ('kallithea.lib.utils', 'kallithea.model'), # clean up utils | |
160 | ('kallithea.lib.utils', 'kallithea.model.db'), |
|
161 | ('kallithea.lib.utils', 'kallithea.model.db'), | |
161 | ('kallithea.lib.utils', 'kallithea.model.scm'), |
|
162 | ('kallithea.lib.utils', 'kallithea.model.scm'), | |
162 | ('kallithea.model', 'kallithea.lib.auth'), # auth.HasXXX |
|
163 | ('kallithea.model', 'kallithea.lib.auth'), # auth.HasXXX | |
163 | ('kallithea.model', 'kallithea.lib.auth_modules'), # validators |
|
164 | ('kallithea.model', 'kallithea.lib.auth_modules'), # validators | |
164 | ('kallithea.model', 'kallithea.lib.hooks'), # clean up hooks |
|
165 | ('kallithea.model', 'kallithea.lib.hooks'), # clean up hooks | |
165 | ('kallithea.model', 'kallithea.model.scm'), |
|
166 | ('kallithea.model', 'kallithea.model.scm'), | |
166 | ('kallithea.model.scm', 'kallithea.lib.hooks'), |
|
167 | ('kallithea.model.scm', 'kallithea.lib.hooks'), | |
167 | ]) |
|
168 | ]) | |
168 |
|
169 | |||
169 | extra_edges = [ |
|
170 | extra_edges = [ | |
170 | ('kallithea.config', 'kallithea.controllers'), # through TG |
|
171 | ('kallithea.config', 'kallithea.controllers'), # through TG | |
171 | ('kallithea.lib.auth', 'kallithea.lib.auth_modules'), # custom loader |
|
172 | ('kallithea.lib.auth', 'kallithea.lib.auth_modules'), # custom loader | |
172 | ] |
|
173 | ] | |
173 |
|
174 | |||
174 |
|
175 | |||
175 | def normalize(s): |
|
176 | def normalize(s): | |
176 | """Given a string with dot path, return the string it should be shown as.""" |
|
177 | """Given a string with dot path, return the string it should be shown as.""" | |
177 | parts = s.replace('.__init__', '').split('.') |
|
178 | parts = s.replace('.__init__', '').split('.') | |
178 | short_2 = '.'.join(parts[:2]) |
|
179 | short_2 = '.'.join(parts[:2]) | |
179 | short_3 = '.'.join(parts[:3]) |
|
180 | short_3 = '.'.join(parts[:3]) | |
180 | short_4 = '.'.join(parts[:4]) |
|
181 | short_4 = '.'.join(parts[:4]) | |
181 | if parts[0] in ['scripts', 'contributor_data', 'i18n_utils']: |
|
182 | if parts[0] in ['scripts', 'contributor_data', 'i18n_utils']: | |
182 | return 'scripts' |
|
183 | return 'scripts' | |
183 | if short_3 == 'kallithea.model.meta': |
|
184 | if short_3 == 'kallithea.model.meta': | |
184 | return 'kallithea.model.db' |
|
185 | return 'kallithea.model.db' | |
185 | if parts[:4] == ['kallithea', 'lib', 'vcs', 'ssh']: |
|
186 | if parts[:4] == ['kallithea', 'lib', 'vcs', 'ssh']: | |
186 | return 'kallithea.lib.vcs.ssh' |
|
187 | return 'kallithea.lib.vcs.ssh' | |
187 | if short_4 in shown_modules: |
|
188 | if short_4 in shown_modules: | |
188 | return short_4 |
|
189 | return short_4 | |
189 | if short_3 in shown_modules: |
|
190 | if short_3 in shown_modules: | |
190 | return short_3 |
|
191 | return short_3 | |
191 | if short_2 in shown_modules: |
|
192 | if short_2 in shown_modules: | |
192 | return short_2 |
|
193 | return short_2 | |
193 | if short_2 == 'kallithea.tests': |
|
194 | if short_2 == 'kallithea.tests': | |
194 | return None |
|
195 | return None | |
195 | if parts[0] in ignored_modules: |
|
196 | if parts[0] in ignored_modules: | |
196 | return None |
|
197 | return None | |
197 | assert parts[0] in bottom_external_modules, parts |
|
198 | assert parts[0] in bottom_external_modules, parts | |
198 | return parts[0] |
|
199 | return parts[0] | |
199 |
|
200 | |||
200 |
|
201 | |||
201 | def main(filenames): |
|
202 | def main(filenames): | |
202 | if not filenames or filenames[0].startswith('-'): |
|
203 | if not filenames or filenames[0].startswith('-'): | |
203 | print('''\ |
|
204 | print('''\ | |
204 | Usage: |
|
205 | Usage: | |
205 | hg files 'set:!binary()&grep("^#!.*python")' 'set:**.py' | xargs scripts/deps.py |
|
206 | hg files 'set:!binary()&grep("^#!.*python")' 'set:**.py' | xargs scripts/deps.py | |
206 | dot -Tsvg deps.dot > deps.svg |
|
207 | dot -Tsvg deps.dot > deps.svg | |
207 | ''') |
|
208 | ''') | |
208 | raise SystemExit(1) |
|
209 | raise SystemExit(1) | |
209 |
|
210 | |||
210 | files_imports = dict() # map filenames to its imports |
|
211 | files_imports = dict() # map filenames to its imports | |
211 | import_deps = set() # set of tuples with module name and its imports |
|
212 | import_deps = set() # set of tuples with module name and its imports | |
212 | for fn in filenames: |
|
213 | for fn in filenames: | |
213 | with open(fn) as f: |
|
214 | with open(fn) as f: | |
214 | s = f.read() |
|
215 | s = f.read() | |
215 |
|
216 | |||
216 | dot_name = (fn[:-3] if fn.endswith('.py') else fn).replace('/', '.') |
|
217 | dot_name = (fn[:-3] if fn.endswith('.py') else fn).replace('/', '.') | |
217 | file_imports = set() |
|
218 | file_imports = set() | |
218 | for m in re.finditer(r'^ *(?:from ([^ ]*) import (?:([a-zA-Z].*)|\(([^)]*)\))|import (.*))$', s, re.MULTILINE): |
|
219 | for m in re.finditer(r'^ *(?:from ([^ ]*) import (?:([a-zA-Z].*)|\(([^)]*)\))|import (.*))$', s, re.MULTILINE): | |
219 | m_from, m_from_import, m_from_import2, m_import = m.groups() |
|
220 | m_from, m_from_import, m_from_import2, m_import = m.groups() | |
220 | if m_from: |
|
221 | if m_from: | |
221 | pre = m_from + '.' |
|
222 | pre = m_from + '.' | |
222 | if pre.startswith('.'): |
|
223 | if pre.startswith('.'): | |
223 | pre = dot_name.rsplit('.', 1)[0] + pre |
|
224 | pre = dot_name.rsplit('.', 1)[0] + pre | |
224 | importlist = m_from_import or m_from_import2 |
|
225 | importlist = m_from_import or m_from_import2 | |
225 | else: |
|
226 | else: | |
226 | pre = '' |
|
227 | pre = '' | |
227 | importlist = m_import |
|
228 | importlist = m_import | |
228 | for imp in importlist.split('#', 1)[0].split(','): |
|
229 | for imp in importlist.split('#', 1)[0].split(','): | |
229 | full_imp = pre + imp.strip().split(' as ', 1)[0] |
|
230 | full_imp = pre + imp.strip().split(' as ', 1)[0] | |
230 | file_imports.add(full_imp) |
|
231 | file_imports.add(full_imp) | |
231 | import_deps.add((dot_name, full_imp)) |
|
232 | import_deps.add((dot_name, full_imp)) | |
232 | files_imports[fn] = file_imports |
|
233 | files_imports[fn] = file_imports | |
233 |
|
234 | |||
234 | # dump out all deps for debugging and analysis |
|
235 | # dump out all deps for debugging and analysis | |
235 | with open('deps.txt', 'w') as f: |
|
236 | with open('deps.txt', 'w') as f: | |
236 | for fn, file_imports in sorted(files_imports.items()): |
|
237 | for fn, file_imports in sorted(files_imports.items()): | |
237 | for file_import in sorted(file_imports): |
|
238 | for file_import in sorted(file_imports): | |
238 | if file_import.split('.', 1)[0] in ignored_modules: |
|
239 | if file_import.split('.', 1)[0] in ignored_modules: | |
239 | continue |
|
240 | continue | |
240 | f.write('%s: %s\n' % (fn, file_import)) |
|
241 | f.write('%s: %s\n' % (fn, file_import)) | |
241 |
|
242 | |||
242 | # find leafs that haven't been ignored - they are the important external dependencies and shown in the bottom row |
|
243 | # find leafs that haven't been ignored - they are the important external dependencies and shown in the bottom row | |
243 | only_imported = set( |
|
244 | only_imported = set( | |
244 | set(normalize(b) for a, b in import_deps) - |
|
245 | set(normalize(b) for a, b in import_deps) - | |
245 | set(normalize(a) for a, b in import_deps) - |
|
246 | set(normalize(a) for a, b in import_deps) - | |
246 | set([None, 'kallithea']) |
|
247 | set([None, 'kallithea']) | |
247 | ) |
|
248 | ) | |
248 |
|
249 | |||
249 | normalized_dep_edges = set() |
|
250 | normalized_dep_edges = set() | |
250 | for dot_name, full_imp in import_deps: |
|
251 | for dot_name, full_imp in import_deps: | |
251 | a = normalize(dot_name) |
|
252 | a = normalize(dot_name) | |
252 | b = normalize(full_imp) |
|
253 | b = normalize(full_imp) | |
253 | if a is None or b is None or a == b: |
|
254 | if a is None or b is None or a == b: | |
254 | continue |
|
255 | continue | |
255 | normalized_dep_edges.add((a, b)) |
|
256 | normalized_dep_edges.add((a, b)) | |
256 | #print((dot_name, full_imp, a, b)) |
|
257 | #print((dot_name, full_imp, a, b)) | |
257 | normalized_dep_edges.update(extra_edges) |
|
258 | normalized_dep_edges.update(extra_edges) | |
258 |
|
259 | |||
259 | unseen_shown_modules = shown_modules.difference(a for a, b in normalized_dep_edges).difference(b for a, b in normalized_dep_edges) |
|
260 | unseen_shown_modules = shown_modules.difference(a for a, b in normalized_dep_edges).difference(b for a, b in normalized_dep_edges) | |
260 | assert not unseen_shown_modules, unseen_shown_modules |
|
261 | assert not unseen_shown_modules, unseen_shown_modules | |
261 |
|
262 | |||
262 | with open('deps.dot', 'w') as f: |
|
263 | with open('deps.dot', 'w') as f: | |
263 | f.write('digraph {\n') |
|
264 | f.write('digraph {\n') | |
264 | f.write('subgraph { rank = same; %s}\n' % ''.join('"%s"; ' % s for s in sorted(top_modules))) |
|
265 | f.write('subgraph { rank = same; %s}\n' % ''.join('"%s"; ' % s for s in sorted(top_modules))) | |
265 | f.write('subgraph { rank = same; %s}\n' % ''.join('"%s"; ' % s for s in sorted(only_imported))) |
|
266 | f.write('subgraph { rank = same; %s}\n' % ''.join('"%s"; ' % s for s in sorted(only_imported))) | |
266 | for a, b in sorted(normalized_dep_edges): |
|
267 | for a, b in sorted(normalized_dep_edges): | |
267 | f.write(' "%s" -> "%s"%s\n' % (a, b, ' [color=red]' if (a, b) in known_violations else ' [color=green]' if (a, b) in extra_edges else '')) |
|
268 | f.write(' "%s" -> "%s"%s\n' % (a, b, ' [color=red]' if (a, b) in known_violations else ' [color=green]' if (a, b) in extra_edges else '')) | |
268 | f.write('}\n') |
|
269 | f.write('}\n') | |
269 |
|
270 | |||
270 | # verify dependencies by untangling dependency chain bottom-up: |
|
271 | # verify dependencies by untangling dependency chain bottom-up: | |
271 | todo = set(normalized_dep_edges) |
|
272 | todo = set(normalized_dep_edges) | |
272 | unseen_violations = known_violations.difference(todo) |
|
273 | unseen_violations = known_violations.difference(todo) | |
273 | assert not unseen_violations, unseen_violations |
|
274 | assert not unseen_violations, unseen_violations | |
274 | for x in known_violations: |
|
275 | for x in known_violations: | |
275 | todo.remove(x) |
|
276 | todo.remove(x) | |
276 |
|
277 | |||
277 | while todo: |
|
278 | while todo: | |
278 | depending = set(a for a, b in todo) |
|
279 | depending = set(a for a, b in todo) | |
279 | depended = set(b for a, b in todo) |
|
280 | depended = set(b for a, b in todo) | |
280 | drop = depended - depending |
|
281 | drop = depended - depending | |
281 | if not drop: |
|
282 | if not drop: | |
282 | print('ERROR: cycles:', len(todo)) |
|
283 | print('ERROR: cycles:', len(todo)) | |
283 | for x in sorted(todo): |
|
284 | for x in sorted(todo): | |
284 | print('%s,' % (x,)) |
|
285 | print('%s,' % (x,)) | |
285 | raise SystemExit(1) |
|
286 | raise SystemExit(1) | |
286 | #for do_b in sorted(drop): |
|
287 | #for do_b in sorted(drop): | |
287 | # print('Picking', do_b, '- unblocks:', ' '.join(a for a, b in sorted((todo)) if b == do_b)) |
|
288 | # print('Picking', do_b, '- unblocks:', ' '.join(a for a, b in sorted((todo)) if b == do_b)) | |
288 | todo = set((a, b) for a, b in todo if b in depending) |
|
289 | todo = set((a, b) for a, b in todo if b in depending) | |
289 | #print() |
|
290 | #print() | |
290 |
|
291 | |||
291 |
|
292 | |||
292 | if __name__ == '__main__': |
|
293 | if __name__ == '__main__': | |
293 | main(sys.argv[1:]) |
|
294 | main(sys.argv[1:]) |
General Comments 0
You need to be logged in to leave comments.
Login now