summaryrefslogtreecommitdiffstats
path: root/meta/packages/python/python-urlgrabber/urlgrabber-HEAD.patch
diff options
context:
space:
mode:
Diffstat (limited to 'meta/packages/python/python-urlgrabber/urlgrabber-HEAD.patch')
-rw-r--r--meta/packages/python/python-urlgrabber/urlgrabber-HEAD.patch142
1 files changed, 142 insertions, 0 deletions
diff --git a/meta/packages/python/python-urlgrabber/urlgrabber-HEAD.patch b/meta/packages/python/python-urlgrabber/urlgrabber-HEAD.patch
new file mode 100644
index 0000000000..90180d29a0
--- /dev/null
+++ b/meta/packages/python/python-urlgrabber/urlgrabber-HEAD.patch
@@ -0,0 +1,142 @@
1diff --git a/urlgrabber/grabber.py b/urlgrabber/grabber.py
2index e090e90..a26880c 100644
3--- a/urlgrabber/grabber.py
4+++ b/urlgrabber/grabber.py
5@@ -439,6 +439,12 @@ try:
6 except:
7 __version__ = '???'
8
9+try:
10+ # this part isn't going to do much - need to talk to gettext
11+ from i18n import _
12+except ImportError, msg:
13+ def _(st): return st
14+
15 ########################################################################
16 # functions for debugging output. These functions are here because they
17 # are also part of the module initialization.
18@@ -1052,7 +1058,8 @@ class PyCurlFileObject():
19 self._reget_length = 0
20 self._prog_running = False
21 self._error = (None, None)
22- self.size = None
23+ self.size = 0
24+ self._hdr_ended = False
25 self._do_open()
26
27
28@@ -1085,9 +1092,14 @@ class PyCurlFileObject():
29 return -1
30
31 def _hdr_retrieve(self, buf):
32+ if self._hdr_ended:
33+ self._hdr_dump = ''
34+ self.size = 0
35+ self._hdr_ended = False
36+
37 if self._over_max_size(cur=len(self._hdr_dump),
38 max_size=self.opts.max_header_size):
39- return -1
40+ return -1
41 try:
42 self._hdr_dump += buf
43 # we have to get the size before we do the progress obj start
44@@ -1104,7 +1116,17 @@ class PyCurlFileObject():
45 s = parse150(buf)
46 if s:
47 self.size = int(s)
48-
49+
50+ if buf.lower().find('location') != -1:
51+ location = ':'.join(buf.split(':')[1:])
52+ location = location.strip()
53+ self.scheme = urlparse.urlsplit(location)[0]
54+ self.url = location
55+
56+ if len(self._hdr_dump) != 0 and buf == '\r\n':
57+ self._hdr_ended = True
58+ if DEBUG: DEBUG.info('header ended:')
59+
60 return len(buf)
61 except KeyboardInterrupt:
62 return pycurl.READFUNC_ABORT
63@@ -1136,6 +1158,7 @@ class PyCurlFileObject():
64 self.curl_obj.setopt(pycurl.PROGRESSFUNCTION, self._progress_update)
65 self.curl_obj.setopt(pycurl.FAILONERROR, True)
66 self.curl_obj.setopt(pycurl.OPT_FILETIME, True)
67+ self.curl_obj.setopt(pycurl.FOLLOWLOCATION, True)
68
69 if DEBUG:
70 self.curl_obj.setopt(pycurl.VERBOSE, True)
71@@ -1291,7 +1314,12 @@ class PyCurlFileObject():
72 raise err
73
74 elif str(e.args[1]) == '' and self.http_code != 0: # fake it until you make it
75- msg = 'HTTP Error %s : %s ' % (self.http_code, self.url)
76+ if self.scheme in ['http', 'https']:
77+ msg = 'HTTP Error %s : %s ' % (self.http_code, self.url)
78+ elif self.scheme in ['ftp']:
79+ msg = 'FTP Error %s : %s ' % (self.http_code, self.url)
80+ else:
81+ msg = "Unknown Error: URL=%s , scheme=%s" % (self.url, self.scheme)
82 else:
83 msg = 'PYCURL ERROR %s - "%s"' % (errcode, str(e.args[1]))
84 code = errcode
85@@ -1299,6 +1327,12 @@ class PyCurlFileObject():
86 err.code = code
87 err.exception = e
88 raise err
89+ else:
90+ if self._error[1]:
91+ msg = self._error[1]
92+ err = URLGRabError(14, msg)
93+ err.url = self.url
94+ raise err
95
96 def _do_open(self):
97 self.curl_obj = _curl_cache
98@@ -1532,11 +1566,14 @@ class PyCurlFileObject():
99 def _over_max_size(self, cur, max_size=None):
100
101 if not max_size:
102- max_size = self.size
103- if self.opts.size: # if we set an opts size use that, no matter what
104- max_size = self.opts.size
105+ if not self.opts.size:
106+ max_size = self.size
107+ else:
108+ max_size = self.opts.size
109+
110 if not max_size: return False # if we have None for all of the Max then this is dumb
111- if cur > max_size + max_size*.10:
112+
113+ if cur > int(float(max_size) * 1.10):
114
115 msg = _("Downloaded more than max size for %s: %s > %s") \
116 % (self.url, cur, max_size)
117@@ -1582,7 +1619,11 @@ class PyCurlFileObject():
118 self.opts.progress_obj.end(self._amount_read)
119 self.fo.close()
120
121-
122+ def geturl(self):
123+ """ Provide the geturl() method, used to be got from
124+ urllib.addinfourl, via. urllib.URLopener.* """
125+ return self.url
126+
127 _curl_cache = pycurl.Curl() # make one and reuse it over and over and over
128
129
130diff --git a/urlgrabber/progress.py b/urlgrabber/progress.py
131index dd07c6a..45eb248 100644
132--- a/urlgrabber/progress.py
133+++ b/urlgrabber/progress.py
134@@ -658,6 +658,8 @@ def format_time(seconds, use_hours=0):
135 if seconds is None or seconds < 0:
136 if use_hours: return '--:--:--'
137 else: return '--:--'
138+ elif seconds == float('inf'):
139+ return 'Infinite'
140 else:
141 seconds = int(seconds)
142 minutes = seconds / 60