Python2/3 compat - urllib

[joerg]

docs/tools/dump_ast_matchers.py

11

Missing follow-up change in the rest of the file.

[serge-sans-paille]

Thanks for spotting that, I messed up during the (huge) git add -p session :p

[michaelplatings]

tools/scan-view/bin/scan-view

15

Python 3's urlopen is equivalent to urllib2.urlopen not urllib.urlopen so I recommend importing from urllib2 instead.

[michaelplatings]

tools/scan-view/bin/scan-view

15

This should be the same as dump_ast_matchers.py i.e.:

try:
    from urllib.request import urlopen
except ImportError:
    from urllib2 import urlopen

[michaelplatings]

tools/scan-view/bin/scan-view

15

This still isn't done.

[serge-sans-paille]

Sorry for the noise :-/

[michaelplatings]

LGTM

docs/tools/dump_ast_matchers.py

 #!/usr/bin/env python
 # A tool to parse ASTMatchers.h and update the documentation in
 # ../LibASTMatchersReference.html automatically. Run from the
 # directory in which this file is located to update the docs.
 
 import collections
 import re
-import urllib2
+try:
+    from urllib.request import urlopen
+except ImportError:
+    from urllib2 import urlopen
 
 MATCHERS_FILE = '../../include/clang/ASTMatchers/ASTMatchers.h'
 
 # Each matcher is documented in one row of the form:
 #   result | name | argA
 # The subsequent row contains the documentation and is hidden by default,
 # becoming visible via javascript when the user clicks the matcher name.
 TD_TEMPLATE="""
def esc(text):
   text = re.sub(r'<', '&lt;', text)
   text = re.sub(r'>', '&gt;', text)
   def link_if_exists(m):
     name = m.group(1)
     url = 'https://clang.llvm.org/doxygen/classclang_1_1%s.html' % name
     if url not in doxygen_probes:
       try:
         print('Probing %s...' % url)
-        urllib2.urlopen(url)
+        urlopen(url)
         doxygen_probes[url] = True
       except:
         doxygen_probes[url] = False
     if doxygen_probes[url]:
       return r'Matcher&lt;<a href="%s">%s</a>&gt;' % (url, name)
     else:
       return m.group(0)
   text = re.sub(

docs/tools/dump_format_style.py

 #!/usr/bin/env python
 # A tool to parse the FormatStyle struct from Format.h and update the
 # documentation in ../ClangFormatStyleOptions.rst automatically.
 # Run from the directory in which this file is located to update the docs.
 
 import collections
 import os
 import re
-import urllib2
 
 CLANG_DIR = os.path.join(os.path.dirname(__file__), '../..')
 FORMAT_STYLE_FILE = os.path.join(CLANG_DIR, 'include/clang/Format/Format.h')
 INCLUDE_STYLE_FILE = os.path.join(CLANG_DIR, 'include/clang/Tooling/Inclusions/IncludeStyle.h')
 DOC_FILE = os.path.join(CLANG_DIR, 'docs/ClangFormatStyleOptions.rst')
 
 
 def substitute(text, tag, contents):

tools/scan-view/bin/scan-view

 #!/usr/bin/env python
 
 from __future__ import print_function
 
 """The clang static analyzer results viewer.
 """
 
 import sys
 import imp
 import os
 import posixpath
 import threading
 import time
-import urllib
+try:
+    from urllib.request import urlopen
+except ImportError:
+    from urllib2 import urlopen
 import webbrowser
 
 # How long to wait for server to start.
 kSleepTimeout = .05
 kMaxSleeps = int(60 / kSleepTimeout)
 
 # Default server parameters
 
 kDefaultHost = '127.0.0.1'
 kDefaultPort = 8181
 kMaxPortsToTry = 100
 
 ###
 
 
 def url_is_up(url):
     try:
-        o = urllib.urlopen(url)
+        o = urlopen(url)
     except IOError:
         return False
     o.close()
     return True
 
 
 def start_browser(port, options):
-    import urllib
     import webbrowser
 
     url = 'http://%s:%d' % (options.host, port)
 
     # Wait for server to start...
     if options.debug:
         sys.stderr.write('%s: Waiting for server.' % sys.argv[0])
         sys.stderr.flush()

tools/scan-view/share/ScanView.py

 from __future__ import print_function
 try:
     from http.server import HTTPServer, SimpleHTTPRequestHandler
 except ImportError:
     from BaseHTTPServer import HTTPServer
     from SimpleHTTPServer import SimpleHTTPRequestHandler
 import os
 import sys
-import urllib, urlparse
+try:
+    from urlparse import urlparse
+    from urllib import unquote
+except ImportError:
+    from urllib.parse import urlparse, unquote
+
 import posixpath
 import StringIO
 import re
 import shutil
 import threading
 import time
 import socket
 import itertools
def parse_query(qs, fields=None):
     if fields is None:
         fields = {}
     for chunk in (_f for _f in qs.split('&') if _f):
         if '=' not in chunk:
             name = chunk
             value = ''
         else:
             name, value = chunk.split('=', 1)
-        name = urllib.unquote(name.replace('+', ' '))
-        value = urllib.unquote(value.replace('+', ' '))
+        name = unquote(name.replace('+', ' '))
+        value = unquote(value.replace('+', ' '))
         item = fields.get(name)
         if item is None:
             fields[name] = [value]
         else:
             item.append(value)
     return fields
 
 class ScanViewRequestHandler(SimpleHTTPRequestHandler):
def send_head(self, fields=None):
         if (self.server.options.onlyServeLocal and
             self.client_address[0] != '127.0.0.1'):
             return self.send_error(401, 'Unauthorized host.')
 
         if fields is None:
             fields = {}
         self.fields = fields
 
-        o = urlparse.urlparse(self.path)
+        o = urlparse(self.path)
         self.fields = parse_query(o.query, fields)
-        path = posixpath.normpath(urllib.unquote(o.path))
+        path = posixpath.normpath(unquote(o.path))
 
         # Split the components and strip the root prefix.
         components = path.split('/')[1:]
         
         # Special case some top-level entries.
         if components:
             name = components[0]
             if len(components)==2: