diff --git a/config/linkcheckerrc b/config/linkcheckerrc index 83e11fe0f..b206dc55d 100644 --- a/config/linkcheckerrc +++ b/config/linkcheckerrc @@ -212,7 +212,7 @@ # ^https?://www\.example\.com/~calvin/ calvin mypass # ^ftp://www\.example\.com/secret/ calvin -# if the website requires a login the URL and optionally the user and +# if the website requires a login, the URL and optionally the user and # password CGI fieldnames can be provided. #loginurl=http://www.example.com/ diff --git a/doc/changelog.txt b/doc/changelog.txt index 7d5ec6491..f85e84abf 100644 --- a/doc/changelog.txt +++ b/doc/changelog.txt @@ -50,7 +50,7 @@ Fixes: Closes: GH bug #521 - cgi: Sanitize configuration. Closes: GH bug #519 -- checking: Use user-supplied authentication and proxies when requestiong +- checking: Use user-supplied authentication and proxies when requesting robot.txt. - plugins: Fix Word file check plugin. Closes: GH bug #530 @@ -84,7 +84,7 @@ Features: Changes: - checking: Ignored URLs are reported earlier now. -- checking: Updated the list of unkonwn or ignored URI schemes. +- checking: Updated the list of unknown or ignored URI schemes. - checking: Internal errors do not disable check threads anymore. - checking: Disable URL length warning for data: URLs. - checking: Do not warn about missing addresses on mailto links that have @@ -134,7 +134,7 @@ Changes: is a maximum redirection limit anyway. Closes: GH bug #444, #419 - checking: Disallowed access by robots.txt is an info now, not - a warning. Otherwise it produces a lot of warnings which + a warning. Otherwise, it produces a lot of warnings which is counter-productive. - checking: Do not check SMTP connections for mailto: URLs anymore. It resulted in lots of false warnings since spam prevention @@ -200,7 +200,7 @@ Changes: Fixes: - checking: Apache Coyote (the HTTP server of Tomcat) sends the wrong - Content-Type on HEAD requests. Automatically fallback to GET in this + Content-Type on HEAD requests. Automatically fall back to GET in this case. Closes: GH bug #414 - checking: Do not use GET on POST forms. @@ -236,7 +236,7 @@ Fixes: 8.3 "Mahna Mahna Killer" (released 6.1.2013) Features: -- project: The Project moved to Github. +- project: The Project moved to GitHub. Closes: GH bug #368 Changes: @@ -860,7 +860,7 @@ Changes: - dependencies: Require and use Python 2.6. - cmdline: Removed deprecated options --no-anchor-caching and --no-proxy-for. -- config: Remove backwards compatilibity parsing and require the +- config: Remove backwards compatibility parsing and require the new multiline configuration syntax. - logging: Use codecs module for proper output encoding. Closes: SF bug #3114624 @@ -907,7 +907,7 @@ Changes: - cmdline: Don't log a warning if URL has been redirected. Closes: SF bug #3078820 - checking: Do not print warnings for HTTP -> HTTPS and HTTPS -> HTTP - redirects any more. + redirects anymore. - logging: Changed comment format in GML output to be able to load the graph in gephi. - gui: Remove timeout and thread options. @@ -1054,7 +1054,7 @@ Changes: - checking: Improved HTML parsing speed: a) The parsers for HTML title and robots.txt meta tags stop after seeing a tag. - b) Anchor references are not always parsed, but onl when the--anchor + b) Anchor references are not always parsed, but only when the--anchor option was given. c) Found HTML links are not queued after parsing the whole file, but directly when found. This also saves some memory. @@ -1074,7 +1074,7 @@ Fixes: Closes: SF bug #2806790 - http: Fixed persistent connection handling: retry connecting to HTTP servers which close persistent connections unexpectedly. -- bookmarks: correctly read the bookmark title from Mozilla places.sqllite +- bookmarks: correctly read the bookmark title from Mozilla places.sqlite - checking: ignore the fragment part (ie. the anchor) of URIs when getting and caching HTTP content; follows the HTTP/1.1 specification which does not include fragments in the protocol. Thanks to Martin von Gagern @@ -1223,7 +1223,7 @@ Features: * Remove gopher: URL checking. Type: feature - Changed: linkcheck/checker/unkonwnurl.py + Changed: linkcheck/checker/unknownurl.py Removed: linkcheck/checker/gopherurl.py 4.9 "Michael Clayton" (released 25.4.2008) @@ -1317,7 +1317,7 @@ Features: Changed: linkcheck/linkparse.py, linkcheck/checker/urlbase.py Closes: SF bug #1831900 - * Try to detect unkonwn URL schemes from the command line, eg. URLs + * Try to detect unknown URL schemes from the command line, eg. URLs like "rtsp://foo". Type: feature Changed: linkchecker, linkcheck/lc_cgi.py, @@ -1358,7 +1358,7 @@ Features: Type: documentation Removed: doc/fr/* - * Correct misnamed colums in create.sql script: r/*string/\1/g + * Correct misnamed columns in create.sql script: r/*string/\1/g Type: bugfix Changed: config/create.sql Closes: SF #1849733 @@ -1594,7 +1594,7 @@ Features: * The default intern pattern matches both http: and https: schemes now. Type: feature - Changed: linckheck/checker/internpaturl.py + Changed: linkcheck/checker/internpaturl.py * If the robots.txt connection times out, don't bother to check the URL but report an error immediately. Avoids having the @@ -1743,8 +1743,8 @@ Features: Type: bugfix Changed: linkcheck/checker/httpurl.py - * Workaround a urllib2.py bug raising ValueError on some failed - HTTP authorisations. + * Work around a urllib2.py bug raising ValueError on some failed + HTTP authorizations. Type: bugfix Closes: SF bug #1250555 Changed: linkcheck/robotparser2.py @@ -2367,7 +2367,7 @@ Features: * All leading directories of a given output log file are created automatically now. Errors creating these directories or opening - the log file for writing abort the checking and print a usage mesage. + the log file for writing abort the checking and print a usage message. Type: feature Changed: linkchecker, linkcheck/logger/__init__.py @@ -2505,7 +2505,7 @@ Features: Type: feature Changed: linkcheck/__init__.py - * Removed debug print statement when issueing linkchecker --help. + * Removed debug print statement when issuing linkchecker --help. Type: bugfix Changed: linkchecker @@ -2631,7 +2631,7 @@ Features: Type: feature Changed: linkcheck/checker/cache.py - * the given user/password authententication is now also used to + * the given user/password authentication is now also used to get robots.txt files. Type: feature Changed: linkcheck/robotparser2.py, linkcheck/checker/cache.py @@ -3041,7 +3041,7 @@ Features: 1.8.9 * recompile with bison 1.875a Changed files: linkcheck/parser/htmlparse.[ch] - * remove stpcpy declaration, fixes compile error on RedHat 7.x + * remove stpcpy declaration, fixes compile error on Red Hat 7.x Changed files: linkcheck/parser/htmlsax.h * clarify keyboard interrupt warning to wait for active connections to finish @@ -3158,9 +3158,9 @@ Features: * Add again python-dns, the Debian package maintainer is unresponsive Added files: linkcheck/DNS/*.py Changed files: INSTALL, setup.py - * You must now use named constants for ANSII color codes + * You must now use named constants for ANSI color codes Changed files: linkcheckerrc, linkcheck/log/ColoredLogger.py - * Release RedHat 8.0 rpm packages. + * Release Red Hat 8.0 rpm packages. Changed files: setup.py, MANIFEST.in * remove --robots-txt from manpage, fix HTZP->HTTP typo Changed files: linkchecker.1 @@ -3243,7 +3243,7 @@ Features: 1.6.2: * Warn about unknown Content-Encodings. Dont parse HTML in this case. - * Support deflate content encoding (snatched from Debians reportbug) + * Support deflate content encoding (snatched from Debian's reportbug) * Add appropriate Accept-Encoding header to HTTP request. * Updated german translations diff --git a/doc/de.po b/doc/de.po index 70437c0bf..a05f076ad 100644 --- a/doc/de.po +++ b/doc/de.po @@ -1027,7 +1027,7 @@ msgstr "B (erforderlich)" # type: Plain text #. type: Plain text #: en/linkchecker.1:267 -msgid "Sets the domain the cookies are valid for." +msgid "Sets the domain for which the cookies are valid." msgstr "Setzt die Domäne für die die Cookies gültig sind." # type: TP @@ -1040,7 +1040,7 @@ msgstr "B (optional)" # type: Plain text #. type: Plain text #: en/linkchecker.1:270 -msgid "Gives the path the cookies are value for; default path is B." +msgid "Gives the path for which the cookies are valid; default path is B." msgstr "Gibt den Pfad für den die Cookies gültig sind; Standardpfad ist B." # type: TP diff --git a/doc/en/linkchecker.1 b/doc/en/linkchecker.1 index 0ba1ad8ed..9f0f569b2 100644 --- a/doc/en/linkchecker.1 +++ b/doc/en/linkchecker.1 @@ -263,10 +263,10 @@ following possible names: . .TP \fBHost\fP (required) -Sets the domain the cookies are valid for. +Sets the domain for which the cookies are valid. .TP \fBPath\fP (optional) -Gives the path the cookies are value for; default path is \fB/\fP. +Gives the path for which the cookies are valid; default path is \fB/\fP. .TP \fBSet-cookie\fP (required) Set cookie name/value. Can be given more than once. @@ -337,7 +337,7 @@ A mailto: link eventually resolves to a list of email addresses. If one address fails, the whole list will fail. For each mail address we check the following things: . - 1) Check the adress syntax, both of the part before and after + 1) Check the address syntax, both of the part before and after the @ sign. 2) Look up the MX DNS records. If we found no MX record, print an error. @@ -352,7 +352,7 @@ FTP links (\fBftp:\fP) For FTP links we do: 1) connect to the specified host - 2) try to login with the given user and password. The default + 2) try to log in with the given user and password. The default user is ``anonymous``, the default password is ``anonymous@``. 3) try to change to the given directory 4) list the file with the NLST command @@ -360,7 +360,7 @@ FTP links (\fBftp:\fP) .TP Telnet links (``telnet:``) - We try to connect and if user/password are given, login to the + We try to connect and if user/password are given, log in to the given telnet server. .TP @@ -432,7 +432,7 @@ connection to the internet (e.g. with diald), it will connect when checking links not pointing to your local host. Use the \fB\-\-ignore\-url\fP option to prevent this. -Javascript links are not supported. +JavaScript links are not supported. If your platform does not support threading, LinkChecker disables it automatically. diff --git a/doc/fr.po b/doc/fr.po index cde102177..fb0f97498 100644 --- a/doc/fr.po +++ b/doc/fr.po @@ -930,7 +930,7 @@ msgstr "" # type: Plain text #: en/linkchecker.1:278 -msgid "Sets the scheme the cookies are valid for; default scheme is B." +msgid "Sets the scheme for which the cookies are valid; default scheme is B." msgstr "" # type: TP @@ -941,7 +941,7 @@ msgstr "" # type: Plain text #: en/linkchecker.1:281 -msgid "Sets the domain the cookies are valid for." +msgid "Sets the domain for which the cookies are valid." msgstr "" # type: TP @@ -952,7 +952,7 @@ msgstr "" # type: Plain text #: en/linkchecker.1:284 -msgid "Gives the path the cookies are value for; default path is B." +msgid "Gives the path for which the cookies are valid; default path is B." msgstr "" # type: TP diff --git a/doc/install.txt b/doc/install.txt index 4734e20a3..d829be14d 100644 --- a/doc/install.txt +++ b/doc/install.txt @@ -29,7 +29,7 @@ in your programs folder Setup for GNU/Linux ------------------- -On all major Linux distributions (Debian, Mandriva, Redhat, Suse, Ubuntu), +On all major Linux distributions (Debian, Mandriva, Red Hat, Suse, Ubuntu), the ``linkchecker`` package is available for install. diff --git a/doc/linkchecker.doc.pot b/doc/linkchecker.doc.pot index d1172646a..83eec89ec 100644 --- a/doc/linkchecker.doc.pot +++ b/doc/linkchecker.doc.pot @@ -787,7 +787,7 @@ msgstr "" #. type: Plain text #: en/linkchecker.1:267 -msgid "Sets the domain the cookies are valid for." +msgid "Sets the domain for which the cookies are valid." msgstr "" #. type: TP @@ -798,7 +798,7 @@ msgstr "" #. type: Plain text #: en/linkchecker.1:270 -msgid "Gives the path the cookies are value for; default path is B." +msgid "Gives the path for which the cookies are valid; default path is B." msgstr "" #. type: TP @@ -972,7 +972,7 @@ msgstr "" #: en/linkchecker.1:349 #, no-wrap msgid "" -" 1) Check the adress syntax, both of the part before and after\n" +" 1) Check the address syntax, both of the part before and after\n" " the @ sign.\n" " 2) Look up the MX DNS records. If we found no MX record,\n" " print an error.\n" @@ -1000,7 +1000,7 @@ msgstr "" #, no-wrap msgid "" " 1) connect to the specified host\n" -" 2) try to login with the given user and password. The default\n" +" 2) try to log in with the given user and password. The default\n" " user is ``anonymous``, the default password is ``anonymous@``.\n" " 3) try to change to the given directory\n" " 4) list the file with the NLST command\n" @@ -1016,7 +1016,7 @@ msgstr "" #: en/linkchecker.1:365 #, no-wrap msgid "" -" We try to connect and if user/password are given, login to the\n" +" We try to connect and if user/password are given, log in to the\n" " given telnet server.\n" msgstr "" @@ -1183,7 +1183,7 @@ msgstr "" #. type: Plain text #: en/linkchecker.1:436 -msgid "Javascript links are not supported." +msgid "JavaScript links are not supported." msgstr "" #. type: Plain text diff --git a/doc/upgrading.txt b/doc/upgrading.txt index 89e71e831..e824e0e7e 100644 --- a/doc/upgrading.txt +++ b/doc/upgrading.txt @@ -132,7 +132,7 @@ Python >= 2.5 is now required. The CGI script access control has been removed. Please use the access control of your webserver to restrict access to the CGI script. -An example configuration file for the Apache weberver has been included +An example configuration file for the Apache webserver has been included in the distribution. Migrating from 4.4 to 4.5 @@ -155,7 +155,7 @@ should be written as: # this is a comment ^nntp: -Note the leading spac(es) at the beginning of each line after +Note the leading space(s) at the beginning of each line after ``ignore=``. If an indented line starts with a comment sign, it will be ignored. @@ -186,7 +186,7 @@ server, so your checking time might increase if the server enforces such a delay through its robots.txt file. URLs with invalid syntax are now cached, and they get matched now by -the --ingore-url option. +the --ignore-url option. Migrating from 3.0 to 3.1 ------------------------- diff --git a/doc/web/content/donations.md b/doc/web/content/donations.md index 35bd24b17..1e0967f0e 100644 --- a/doc/web/content/donations.md +++ b/doc/web/content/donations.md @@ -4,5 +4,5 @@ Hopefully LinkChecker has been useful for you and your projects. In case you are considering to give something back, feel free to send me some money over paypal or klick the flattr button on the right. -If you already donated something I herebay say thanks! +If you already donated something I hereby say thanks! diff --git a/doc/web/media/man1/linkchecker.1.html b/doc/web/media/man1/linkchecker.1.html index 1d0adf7fd..e1b201c40 100644 --- a/doc/web/media/man1/linkchecker.1.html +++ b/doc/web/media/man1/linkchecker.1.html @@ -279,9 +279,9 @@

COOKIE FILES

following possible names:
Host (required)
-Sets the domain the cookies are valid for. +Sets the domain for which the cookies are valid.
Path (optional)
-Gives the path the cookies are value for; default path is /. +Gives the path for which the cookies are valid; default path is /.
Set-cookie (required)
Set cookie name/value. Can be given more than once.
@@ -348,7 +348,7 @@

PERFORMED CHECKS

A mailto: link eventually resolves to a list of email addresses. If one address fails, the whole list will fail. For each mail address we check the following things: -
  1) Check the adress syntax, both of the part before and after +
  1) Check the address syntax, both of the part before and after
     the @ sign.
  2) Look up the MX DNS records. If we found no MX record,
     print an error. @@ -443,7 +443,7 @@

NOTES

checking links not pointing to your local host. Use the --ignore-url option to prevent this.

-Javascript links are not supported. +JavaScript links are not supported.

If your platform does not support threading, LinkChecker disables it automatically. diff --git a/doc/web/media/man5/linkcheckerrc.5.html b/doc/web/media/man5/linkcheckerrc.5.html index db9f3b2c9..d7870b7d6 100644 --- a/doc/web/media/man5/linkcheckerrc.5.html +++ b/doc/web/media/man5/linkcheckerrc.5.html @@ -208,7 +208,7 @@

[filtering]

Command line option: --ignore-url
ignorewarnings=NAME[,NAME...]
Ignore the comma-separated list of warnings. See -WARNIGS for the list of supported warnings. +WARNINGS for the list of supported warnings.
Command line option: none @@ -381,7 +381,7 @@

[text]

colordltime=STRING
Set download time color. Default is default.
colorreset=STRING
-Set reset color. Default is deault. +Set reset color. Default is default.  

[gml]

diff --git a/linkcheck/HtmlParser/__init__.py b/linkcheck/HtmlParser/__init__.py index a99ec6a88..7e6540d6c 100644 --- a/linkcheck/HtmlParser/__init__.py +++ b/linkcheck/HtmlParser/__init__.py @@ -60,7 +60,7 @@ - Speed The FLEX code is configured to generate a large but fast scanner. The parser ignores forbidden or unnecessary HTML end tags. - The parser converts tag and attribute names to lower case for easier + The parser converts tag and attribute names to lowercase for easier matching. The parser quotes all attribute values. Python memory management interface is used. @@ -215,7 +215,7 @@ def resolve_entities (s): _encoding_ro = re.compile(r"charset=(?P[-0-9a-zA-Z]+)") -def set_encoding (parsobj, attrs): +def set_encoding (parserobj, attrs): """ Set document encoding for the HTML parser according to the tag attribute information. @@ -235,7 +235,7 @@ def set_encoding (parsobj, attrs): charset = charset.encode('ascii', 'ignore').lower() charset = get_ctype_charset(charset) if charset and charset in SUPPORTED_CHARSETS: - parsobj.encoding = charset + parserobj.encoding = charset def get_ctype_charset (text): @@ -255,7 +255,7 @@ def get_ctype_charset (text): return None -def set_doctype (parsobj, doctype): +def set_doctype (parserobj, doctype): """ Set document type of the HTML parser according to the given document type string. @@ -265,4 +265,4 @@ def set_doctype (parsobj, doctype): @return: None """ if u"XHTML" in doctype: - parsobj.doctype = "XHTML" + parserobj.doctype = "XHTML" diff --git a/linkcheck/HtmlParser/htmllex.c b/linkcheck/HtmlParser/htmllex.c index 6b06bc4d2..927635eed 100644 --- a/linkcheck/HtmlParser/htmllex.c +++ b/linkcheck/HtmlParser/htmllex.c @@ -315,7 +315,7 @@ struct yy_buffer_state #define YY_BUFFER_NORMAL 1 /* When an EOF's been seen but there's still some text to process * then we mark the buffer as YY_EOF_PENDING, to indicate that we - * shouldn't try reading from the input source any more. We might + * shouldn't try reading from the input source anymore. We might * still have a bunch of tokens to match, though, because of * possible backing-up. * @@ -5476,7 +5476,7 @@ static void yyensure_buffer_stack (yyscan_t yyscanner) /* %endif */ /* %if-c-only */ -/** Setup the input buffer state to scan directly from a user-specified character buffer. +/** Set up the input buffer state to scan directly from a user-specified character buffer. * @param base the character buffer * @param size the size in bytes of the character buffer * @param yyscanner The scanner object. @@ -5513,7 +5513,7 @@ YY_BUFFER_STATE yy_scan_buffer (char * base, yy_size_t size , yyscan_t yyscann /* %endif */ /* %if-c-only */ -/** Setup the input buffer state to scan a string. The next call to yylex() will +/** Set up the input buffer state to scan a string. The next call to yylex() will * scan from a @e copy of @a str. * @param yystr a NUL-terminated string to scan * @param yyscanner The scanner object. @@ -5529,7 +5529,7 @@ YY_BUFFER_STATE yy_scan_string (yyconst char * yystr , yyscan_t yyscanner) /* %endif */ /* %if-c-only */ -/** Setup the input buffer state to scan the given bytes. The next call to yylex() will +/** Set up the input buffer state to scan the given bytes. The next call to yylex() will * scan from a @e copy of @a bytes. * @param yybytes the byte buffer to scan * @param _yybytes_len the number of bytes in the buffer pointed to by @a bytes. diff --git a/linkcheck/HtmlParser/htmlparse.c b/linkcheck/HtmlParser/htmlparse.c index 71615b4db..34ddd7c1d 100644 --- a/linkcheck/HtmlParser/htmlparse.c +++ b/linkcheck/HtmlParser/htmlparse.c @@ -1408,7 +1408,7 @@ YYSTYPE yylval YY_INITIAL_VALUE (= yyval_default); case 5: #line 209 "htmlparse.y" /* yacc.c:1646 */ { - /* an error occured in the scanner, the python exception must be set */ + /* an error occurred in the scanner, the python exception must be set */ UserData* ud = yyget_extra(scanner); PyErr_Fetch(&(ud->exc_type), &(ud->exc_val), &(ud->exc_tb)); YYABORT; diff --git a/linkcheck/HtmlParser/htmlparse.y b/linkcheck/HtmlParser/htmlparse.y index 635a33c20..f22582ee6 100644 --- a/linkcheck/HtmlParser/htmlparse.y +++ b/linkcheck/HtmlParser/htmlparse.y @@ -207,7 +207,7 @@ element: T_WAIT { } | T_ERROR { - /* an error occured in the scanner, the python exception must be set */ + /* an error occurred in the scanner, the python exception must be set */ UserData* ud = yyget_extra(scanner); PyErr_Fetch(&(ud->exc_type), &(ud->exc_val), &(ud->exc_tb)); YYABORT; diff --git a/linkcheck/better_exchook2.py b/linkcheck/better_exchook2.py index ea9c5eda6..643774999 100644 --- a/linkcheck/better_exchook2.py +++ b/linkcheck/better_exchook2.py @@ -200,8 +200,8 @@ def _trySet(old, prefix, func): output(' locals:', out=out) alreadyPrintedLocals = set() for tokenstr in grep_full_py_identifiers(parse_py_statement(line)): - splittedtoken = tuple(tokenstr.split(".")) - for token in map(lambda i: splittedtoken[0:i], range(1, len(splittedtoken) + 1)): + splittoken = tuple(tokenstr.split(".")) + for token in map(lambda i: splittoken[0:i], range(1, len(splittoken) + 1)): if token in alreadyPrintedLocals: continue tokenvalue = None tokenvalue = _trySet(tokenvalue, " ", lambda: pretty_print(_resolveIdentifier(f.f_locals, token))) diff --git a/linkcheck/checker/__init__.py b/linkcheck/checker/__init__.py index 02152b188..545a886e6 100644 --- a/linkcheck/checker/__init__.py +++ b/linkcheck/checker/__init__.py @@ -108,7 +108,7 @@ def get_url_from (base_url, recursion_level, aggregate, else: scheme = None if not (url or name): - # use filename as base url, with slash as path seperator + # use filename as base url, with slash as path separator name = base_url.replace("\\", "/") allowed_schemes = aggregate.config["allowedschemes"] # ignore local PHP files with execution directives diff --git a/linkcheck/checker/const.py b/linkcheck/checker/const.py index 504ba9ce0..98101fd4c 100644 --- a/linkcheck/checker/const.py +++ b/linkcheck/checker/const.py @@ -39,7 +39,7 @@ DNSException, socket.error, select.error, - # nttp errors (including EOFError) + # nntp errors (including EOFError) nntplib.NNTPError, EOFError, # http errors diff --git a/linkcheck/checker/httpurl.py b/linkcheck/checker/httpurl.py index 6f207b6e5..18c741d56 100644 --- a/linkcheck/checker/httpurl.py +++ b/linkcheck/checker/httpurl.py @@ -20,7 +20,7 @@ import requests # The validity of SSL certs is ignored to be able -# the check the URL and recurse into it. +# to check the URL and recurse into it. # The warning about invalid SSL certs is given to the # user instead. import warnings diff --git a/linkcheck/checker/nntpurl.py b/linkcheck/checker/nntpurl.py index f1d64dcd6..693aa07a1 100644 --- a/linkcheck/checker/nntpurl.py +++ b/linkcheck/checker/nntpurl.py @@ -54,7 +54,7 @@ def check_connection (self): number = nntp.stat("<"+group+">")[1] self.add_info(_('Article number %(num)s found.') % {"num": number}) else: - # split off trailing articel span + # split off trailing article span group = group.split('/', 1)[0] if group: # request group info (resp, count, first, last, name) diff --git a/linkcheck/checker/urlbase.py b/linkcheck/checker/urlbase.py index aa4adc4ac..f94c26d80 100644 --- a/linkcheck/checker/urlbase.py +++ b/linkcheck/checker/urlbase.py @@ -612,7 +612,7 @@ def set_content_type (self): pass def can_get_content (self): - """Indicate wether url get_content() can be called.""" + """Indicate whether url get_content() can be called.""" return self.size <= self.aggregate.config["maxfilesizedownload"] def get_content (self): @@ -837,6 +837,6 @@ class CompactUrlData (object): __slots__ = urlDataAttr def __init__(self, wired_url_data): - '''Set all attributes according to the dictionnary wired_url_data''' + '''Set all attributes according to the dictionary wired_url_data''' for attr in urlDataAttr: setattr(self, attr, wired_url_data[attr]) diff --git a/linkcheck/configuration/__init__.py b/linkcheck/configuration/__init__.py index fc2c148a4..3874ba422 100644 --- a/linkcheck/configuration/__init__.py +++ b/linkcheck/configuration/__init__.py @@ -484,7 +484,7 @@ def get_kde_ftp_proxy (): log.debug(LOG_CHECK, "error getting FTP proxy from KDE: %s", msg) pass -# The following KDE functions are largely ported and ajusted from +# The following KDE functions are largely ported and adjusted from # Google Chromium: # http://src.chromium.org/viewvc/chrome/trunk/src/net/proxy/proxy_config_service_linux.cc?revision=HEAD&view=markup # Copyright (c) 2010 The Chromium Authors. All rights reserved. diff --git a/linkcheck/decorators.py b/linkcheck/decorators.py index 1831537f5..28e421c11 100644 --- a/linkcheck/decorators.py +++ b/linkcheck/decorators.py @@ -102,7 +102,7 @@ def newfunc (*args, **kwargs): def synchronized (lock): - """A decorator calling a function with aqcuired lock.""" + """A decorator calling a function with acquired lock.""" return lambda func: synchronize(lock, func) diff --git a/linkcheck/director/checker.py b/linkcheck/director/checker.py index 1f6941031..c6cf50f81 100644 --- a/linkcheck/director/checker.py +++ b/linkcheck/director/checker.py @@ -24,7 +24,7 @@ from .. import parser # Interval in which each check thread looks if it's stopped. -QUEUE_POLL_INTERVALL_SECS = 1.0 +QUEUE_POLL_INTERVAL_SECS = 1.0 def check_urls (urlqueue, logger): @@ -98,7 +98,7 @@ def run_checked (self): def check_url (self): """Try to get URL data from queue and check it.""" try: - url_data = self.urlqueue.get(timeout=QUEUE_POLL_INTERVALL_SECS) + url_data = self.urlqueue.get(timeout=QUEUE_POLL_INTERVAL_SECS) if url_data is not None: try: self.check_url_data(url_data) diff --git a/linkcheck/fileutil.py b/linkcheck/fileutil.py index b461e9360..b47837d12 100644 --- a/linkcheck/fileutil.py +++ b/linkcheck/fileutil.py @@ -69,7 +69,7 @@ def has_module (name, without_error=True): except ImportError: return False except Exception: - # some modules raise errors when intitializing + # some modules raise errors when initializing return not without_error diff --git a/linkcheck/ftpparse.py b/linkcheck/ftpparse.py index fc2449fa8..d2572aa25 100644 --- a/linkcheck/ftpparse.py +++ b/linkcheck/ftpparse.py @@ -106,7 +106,7 @@ def ftpparse (line): # MultiNet (some spaces removed from examples) # "00README.TXT;1 2 30-DEC-1996 17:44 [SYSTEM] (RWED,RWED,RE,RE)" # "CORE.DIR;1 1 8-SEP-1996 16:09 [SYSTEM] (RWE,RWE,RE,RE)" - # and non-MutliNet VMS: + # and non-MultiNet VMS: # "CII-MANUAL.TEX;1 213/216 29-JAN-1996 03:33:12 [ANONYMOU,ANONYMOUS] (RWED,RWED,,)" i = line.find(';') if i != -1: diff --git a/linkcheck/gzip2.py b/linkcheck/gzip2.py index 69d913e52..209f9293a 100644 --- a/linkcheck/gzip2.py +++ b/linkcheck/gzip2.py @@ -333,7 +333,7 @@ def _add_read_data(self, data): def _read_eof(self): # We've read to the end of the file, so we have to rewind in order # to reread the 8 bytes containing the CRC and the file size. - # We check the that the computed CRC and size of the + # We check that the computed CRC and size of the # uncompressed data matches the stored values. Note that the size # stored is the true file size mod 2**32. self.fileobj.seek(-8, 1) diff --git a/linkcheck/i18n.py b/linkcheck/i18n.py index 1bfd2da6f..e220eaf28 100644 --- a/linkcheck/i18n.py +++ b/linkcheck/i18n.py @@ -18,7 +18,7 @@ Application internationalization support. """ -# i18n suppport +# i18n support import os import locale import gettext @@ -89,7 +89,7 @@ def init (domain, directory, loc=None): else: default_language = "en" # Even if the default language is not supported, the encoding should - # be installed. Otherwise the Python installation is borked. + # be installed. Otherwise, the Python installation is borked. default_encoding = encoding install_language(default_language) @@ -178,23 +178,23 @@ def norm_locale (loc): return loc -lang_names = { +lang_name_native = { 'en': u'English', 'de': u'Deutsch', } -lang_transis = { +lang_name_translated = { 'de': {'en': u'German'}, 'en': {'de': u'Englisch'}, } def lang_name (lang): """Return full name of given language.""" - return lang_names[lang] + return lang_name_native[lang] def lang_trans (lang, curlang): """Return translated full name of given language.""" - return lang_transis[lang][curlang] + return lang_name_translated[lang][curlang] def get_encoded_writer (out=sys.stdout, encoding=None, errors='replace'): diff --git a/linkcheck/lc_cgi.py b/linkcheck/lc_cgi.py index 3cba2d043..f5d3a4acc 100644 --- a/linkcheck/lc_cgi.py +++ b/linkcheck/lc_cgi.py @@ -112,7 +112,7 @@ def write (self, data): @synchronized(_lock) def get_data (self): - """Get bufferd unicode data.""" + """Get buffered unicode data.""" data = u"".join(self.buf) self.buf = [] return data diff --git a/linkcheck/loader.py b/linkcheck/loader.py index 52e182eaa..87bf5775d 100644 --- a/linkcheck/loader.py +++ b/linkcheck/loader.py @@ -92,7 +92,7 @@ def get_plugins(modules, classes): @param modules: the modules to search @ptype modules: iterator of modules @return: found classes - @rytpe: iterator of class objects + @rtype: iterator of class objects """ for module in modules: for plugin in get_module_plugins(module, classes): diff --git a/linkcheck/logger/__init__.py b/linkcheck/logger/__init__.py index 7409e7e9b..63f045da2 100644 --- a/linkcheck/logger/__init__.py +++ b/linkcheck/logger/__init__.py @@ -306,7 +306,7 @@ def write (self, s, **args): self.start_fileoutput() if self.fd is None: # Happens when aborting threads times out - log.warn(LOG_CHECK, "writing to unitialized or closed file") + log.warn(LOG_CHECK, "writing to uninitialized or closed file") else: try: self.fd.write(s, **args) diff --git a/linkcheck/logger/blacklist.py b/linkcheck/logger/blacklist.py index e4174c67d..44c416475 100644 --- a/linkcheck/logger/blacklist.py +++ b/linkcheck/logger/blacklist.py @@ -37,7 +37,7 @@ class BlacklistLogger (_Logger): } def __init__ (self, **kwargs): - """Intialize with old blacklist data (if found, else not).""" + """Initialize with old blacklist data (if found, else not).""" args = self.get_args(kwargs) super(BlacklistLogger, self).__init__(**args) self.init_fileoutput(args) diff --git a/linkcheck/memoryutil.py b/linkcheck/memoryutil.py index 5dab9656e..e340ff1db 100644 --- a/linkcheck/memoryutil.py +++ b/linkcheck/memoryutil.py @@ -36,7 +36,7 @@ def write_memory_dump(): # first do a full garbage collection run gc.collect() if gc.garbage: - log.warn(LOG_CHECK, "Unreachabe objects: %s", pprint.pformat(gc.garbage)) + log.warn(LOG_CHECK, "Unreachable objects: %s", pprint.pformat(gc.garbage)) from meliae import scanner fo, filename = get_temp_file(mode='wb', suffix='.json', prefix='lcdump_') try: diff --git a/linkcheck/network/iputil.py b/linkcheck/network/iputil.py index 1f89468fb..a24c83dbc 100644 --- a/linkcheck/network/iputil.py +++ b/linkcheck/network/iputil.py @@ -24,8 +24,8 @@ from .. import log, LOG_CHECK -# IP Adress regular expressions -# Note that each IPv4 octet can be encoded in dezimal, hexadezimal and octal. +# IP Address regular expressions +# Note that each IPv4 octet can be encoded in decimal, hexadecimal and octal. _ipv4_num = r"\d{1,3}" _ipv4_hex = r"0*[\da-f]{1,2}" _ipv4_oct = r"0+[0-7]{0, 3}" @@ -203,7 +203,7 @@ def strhosts2map (strhosts): def hosts2map (hosts): """ Return a set of named hosts, and a list of subnets (host/netmask - adresses). + addresses). Only IPv4 host/netmasks are supported. """ hostset = set() diff --git a/linkcheck/plugins/locationinfo.py b/linkcheck/plugins/locationinfo.py index cf093ef61..8aa7ce847 100644 --- a/linkcheck/plugins/locationinfo.py +++ b/linkcheck/plugins/locationinfo.py @@ -89,7 +89,7 @@ def get_geoip_dat (): def get_location (host): """Get translated country and optional city name. - @return: country with optional city or an boolean False if not found + @return: country with optional city or a boolean False if not found """ if geoip is None: # no geoip available diff --git a/linkcheck/plugins/sslcertcheck.py b/linkcheck/plugins/sslcertcheck.py index b56b6c3c2..2d805f382 100644 --- a/linkcheck/plugins/sslcertcheck.py +++ b/linkcheck/plugins/sslcertcheck.py @@ -75,16 +75,16 @@ def check_ssl_valid_date(self, url_data, cert): try: notAfter = ssl.cert_time_to_seconds(cert['notAfter']) except ValueError as msg: - msg = _('Invalid SSL certficate "notAfter" value %r') % cert['notAfter'] + msg = _('Invalid SSL certificate "notAfter" value %r') % cert['notAfter'] url_data.add_warning(msg) return curTime = time.time() - # Calculate seconds until certifcate expires. Can be negative if + # Calculate seconds until certificate expires. Can be negative if # the certificate is already expired. secondsValid = notAfter - curTime args = dict(expire=cert['notAfter']) if secondsValid < 0: - msg = _('SSL certficate is expired on %(expire)s.') + msg = _('SSL certificate is expired on %(expire)s.') url_data.add_warning(msg % args) else: args['valid'] = strformat.strduration_long(secondsValid) diff --git a/linkcheck/robotparser2.py b/linkcheck/robotparser2.py index 91b9548ca..c7bb62c1d 100644 --- a/linkcheck/robotparser2.py +++ b/linkcheck/robotparser2.py @@ -61,7 +61,7 @@ def _reset (self): self.sitemap_urls = [] def mtime (self): - """Returns the time the robots.txt file was last fetched. + """Returns the time that the robots.txt file was last fetched. This is useful for long-running web spiders that need to check for new robots.txt files periodically. @@ -72,7 +72,7 @@ def mtime (self): return self.last_checked def modified (self): - """Set the time the robots.txt file was last fetched to the + """Set the time that the robots.txt file was last fetched to the current time.""" self.last_checked = time.time() @@ -339,7 +339,7 @@ def allowance (self, filename): - our agent applies to this entry - filename is URL decoded - Check if given filename is allowed to acces this entry. + Check if given filename is allowed to access this entry. @return: True if allowed, else False @rtype: bool diff --git a/linkcheck/strformat.py b/linkcheck/strformat.py index 52a69a743..779375b6c 100644 --- a/linkcheck/strformat.py +++ b/linkcheck/strformat.py @@ -103,7 +103,7 @@ def unquote (s, matching=False): @return: if s evaluates to False, return s as is, else return string with stripped quotes - @rtype: unquoted string, or s unchanged if it is evaluting to False + @rtype: unquoted string, or s unchanged if it is evaluating to False """ if not s: return s diff --git a/linkcheck/url.py b/linkcheck/url.py index 6263fb741..b588f4a64 100644 --- a/linkcheck/url.py +++ b/linkcheck/url.py @@ -454,7 +454,7 @@ def url_needs_quoting (url): """ if url.rstrip() != url: # handle trailing whitespace as a special case - # since '$' matches immediately before a end-of-line + # since '$' matches immediately before an end-of-line return True return not _safe_url_chars_ro.match(url) diff --git a/linkchecker b/linkchecker index 199532cf2..8cc1911fa 100755 --- a/linkchecker +++ b/linkchecker @@ -61,7 +61,7 @@ Notes = _("""NOTES connection to the internet (e.g. with diald), it will connect when checking links not pointing to your local system. See the --ignore-url option on how to prevent this. - o Javascript links are currently ignored. + o JavaScript links are currently ignored. o If your platform does not support threading, LinkChecker disables it automatically. o You can supply multiple user/password pairs in a configuration file. @@ -107,11 +107,11 @@ CookieFormat = _("""COOKIE FILES A cookie file contains standard RFC 805 header data with the following possible names: Scheme (optional) - Sets the scheme the cookies are valid for; default scheme is 'http'. + Sets the scheme for which the cookies are valid; default scheme is 'http'. Host (required) - Sets the domain the cookies are valid for. + Sets the domain for which the cookies are valid. Path (optional) - Gives the path the cookies are value for; default path is '/'. + Gives the path for which the cookies are valid; default path is '/'. Set-cookie (optional) Set cookie name/value. Can be given more than once. diff --git a/po/de.po b/po/de.po index c251ca9fe..e065699ec 100644 --- a/po/de.po +++ b/po/de.po @@ -1262,11 +1262,11 @@ msgid "" "A cookie file contains standard RFC 805 header data with the following\n" "possible names:\n" "Scheme (optional)\n" -" Sets the scheme the cookies are valid for; default scheme is 'http'.\n" +" Sets the scheme for which the cookies are valid; default scheme is 'http'.\n" "Host (required)\n" -" Sets the domain the cookies are valid for.\n" +" Sets the domain for which the cookies are valid.\n" "Path (optional)\n" -" Gives the path the cookies are value for; default path is '/'.\n" +" Gives the path for which the cookies are valid; default path is '/'.\n" "Set-cookie (optional)\n" " Set cookie name/value. Can be given more than once.\n" "\n" diff --git a/po/linkchecker.pot b/po/linkchecker.pot index 7175dece0..e03303f14 100644 --- a/po/linkchecker.pot +++ b/po/linkchecker.pot @@ -258,12 +258,12 @@ msgstr "" #: ../linkcheck/plugins/sslcertcheck.py:78 #, python-format -msgid "Invalid SSL certficate \"notAfter\" value %r" +msgid "Invalid SSL certificate \"notAfter\" value %r" msgstr "" #: ../linkcheck/plugins/sslcertcheck.py:87 #, python-format -msgid "SSL certficate is expired on %(expire)s." +msgid "SSL certificate is expired on %(expire)s." msgstr "" #: ../linkcheck/plugins/sslcertcheck.py:92 @@ -1085,7 +1085,7 @@ msgid "" " connection to the internet (e.g. with diald), it will connect when\n" " checking links not pointing to your local system.\n" " See the --ignore-url option on how to prevent this.\n" -" o Javascript links are currently ignored.\n" +" o JavaScript links are currently ignored.\n" " o If your platform does not support threading, LinkChecker disables it\n" " automatically.\n" " o You can supply multiple user/password pairs in a configuration file.\n" @@ -1138,11 +1138,11 @@ msgid "" "A cookie file contains standard RFC 805 header data with the following\n" "possible names:\n" "Scheme (optional)\n" -" Sets the scheme the cookies are valid for; default scheme is 'http'.\n" +" Sets the scheme for which the cookies are valid; default scheme is 'http'.\n" "Host (required)\n" -" Sets the domain the cookies are valid for.\n" +" Sets the domain for which the cookies are valid.\n" "Path (optional)\n" -" Gives the path the cookies are value for; default path is '/'.\n" +" Gives the path for which the cookies are valid; default path is '/'.\n" "Set-cookie (optional)\n" " Set cookie name/value. Can be given more than once.\n" "\n" diff --git a/setup.py b/setup.py index d5e7bee56..0a8c35f83 100755 --- a/setup.py +++ b/setup.py @@ -91,7 +91,7 @@ def cnormpath (path): release_ro = re.compile(r"\(released (.+)\)") def get_release_date (): - """Parse and return relase date as string from doc/changelog.txt.""" + """Parse and return release date as string from doc/changelog.txt.""" fname = os.path.join("doc", "changelog.txt") release_date = "unknown" with open(fname) as fd: diff --git a/tests/checker/__init__.py b/tests/checker/__init__.py index 6ba5d7bf6..5eb7c9330 100644 --- a/tests/checker/__init__.py +++ b/tests/checker/__init__.py @@ -15,7 +15,7 @@ # with this program; if not, write to the Free Software Foundation, Inc., # 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA. """ -Define standard test support classes funtional for LinkChecker tests. +Define standard test support classes functional for LinkChecker tests. """ import os import re diff --git a/tests/checker/data/file.html.result b/tests/checker/data/file.html.result index 702e8994b..81f8475db 100644 --- a/tests/checker/data/file.html.result +++ b/tests/checker/data/file.html.result @@ -8,7 +8,7 @@ url javascript:loadthis() cache key javascript:loadthis() real url javascript:loadthis() name javascript url -info Javascript URL ignored. +info JavaScript URL ignored. valid url file.html diff --git a/tests/checker/data/urllist.txt.result b/tests/checker/data/urllist.txt.result index 37b79e9b5..0e52f19d8 100644 --- a/tests/checker/data/urllist.txt.result +++ b/tests/checker/data/urllist.txt.result @@ -7,7 +7,7 @@ valid url javascript:loadthis() cache key javascript:loadthis() real url javascript:loadthis() -info Javascript URL ignored. +info JavaScript URL ignored. valid url file.html diff --git a/tests/checker/test_error.py b/tests/checker/test_error.py index 5836ac97d..4ed9331ad 100644 --- a/tests/checker/test_error.py +++ b/tests/checker/test_error.py @@ -53,7 +53,7 @@ def test_invalid1 (self): self.direct(url, resultlines) def test_invalid2 (self): - # missing scheme alltogether + # missing scheme altogether url = u"äöü" attrs = self.get_attrs(url=url) attrs['nurl'] = self.norm("file://%(curdir)s/%(url)s" % attrs) diff --git a/tests/checker/test_mail_bad.py b/tests/checker/test_mail_bad.py index f8f649a2c..c7a77a74d 100644 --- a/tests/checker/test_mail_bad.py +++ b/tests/checker/test_mail_bad.py @@ -34,7 +34,7 @@ def test_error_mail (self): self.mail_error(u'mailto:"a""@example.com', cache_key=u'mailto:a') self.mail_error(u'mailto:""a"@example.com', cache_key=u'mailto:""a"@example.com') self.mail_error(u'mailto:"a\\"@example.com', cache_key=u'mailto:a"@example.com') - # local part unqouted + # local part unquoted self.mail_error(u'mailto:.a@example.com') self.mail_error(u'mailto:a.@example.com') self.mail_error(u'mailto:a..b@example.com') diff --git a/tests/checker/test_news.py b/tests/checker/test_news.py index e0169e672..cfb6baf29 100644 --- a/tests/checker/test_news.py +++ b/tests/checker/test_news.py @@ -26,8 +26,8 @@ NNTP_SERVER = "news.uni-stuttgart.de" # info string returned by news server NNTP_INFO = u"200 news.uni-stuttgart.de InterNetNews NNRP server " \ - u"INN 2.5.2 ready (no posting)" -# Most free NNTP servers are slow, so don't waist a lot of time running those. + u"INN 2.7.1 ready (no posting)" +# Most free NNTP servers are slow, so don't waste a lot of time running those. NNTP_TIMEOUT_SECS = 30 # disabled for now until some stable news server comes up diff --git a/tests/test_clamav.py b/tests/test_clamav.py index 9fe339c87..4541d2c80 100644 --- a/tests/test_clamav.py +++ b/tests/test_clamav.py @@ -36,7 +36,7 @@ def testClean (self): @need_clamav def testInfected (self): - # from the clamav test direcotry: the clamav test file as html data + # from the clamav test directory: the clamav test file as html data data = '