[Lxr-commits] CVS: lxr/lib/LXR/Lang generic.conf,1.39,1.40
Brought to you by:
ajlittoz
Menu
▾
▴
[Lxr-commits] CVS: lxr/lib/LXR/Lang generic.conf,1.39,1.40
|
From: Andre-Littoz <ajl...@us...> - 2013-09-24 10:10:13
|
Update of /cvsroot/lxr/lxr/lib/LXR/Lang In directory sfp-cvs-1.v30.ch3.sourceforge.com:/tmp/cvs-serv10665/lib/LXR/Lang Modified Files: generic.conf Log Message: generic.conf: HTML, JAVA, Make, Pascal, PHP, Python, Ruby include keyword recognition improvement Also, various Perl syntax optimisations Index: generic.conf =================================================================== RCS file: /cvsroot/lxr/lxr/lib/LXR/Lang/generic.conf,v retrieving revision 1.39 retrieving revision 1.40 diff -u -d -r1.39 -r1.40 --- generic.conf 19 Apr 2013 12:42:14 -0000 1.39 +++ generic.conf 24 Sep 2013 10:10:10 -0000 1.40 @@ -8,19 +8,19 @@ # Options to always feed to ectags 'ectagsopts' => - [ "--options=" . $config->ectagsconf - , "--c-types=+plx" - , "--eiffel-types=+l" - , "--fortran-types=+L", + [ '--options=' . $config->{'ectagsconf'} + , '--c-types=+plx' + , '--eiffel-types=+l' + , '--fortran-types=+L' ] # How to map a language name to the ectags language-force name # if there is no mapping, then the language name is used , 'eclangnamemapping' => - { 'C' => 'c' # not necessary as ctags - , 'C++' => 'c++' # seems to take language - , 'Python' => 'python' # names case-insensitive - , 'SQL' => 'SQL2' # -- ctags processing replaced by regexp +# { 'C' => 'c' # not necessary as ctags +# , 'C++' => 'c++' # seems to take language +# , 'Python' => 'python' # names case-insensitive + { 'SQL' => 'SQL2' # -- ctags processing replaced by regexp # (see ectags.conf) # NOTE: language description is not case-insensitive and # makes assumptions about layout of declarations. @@ -110,8 +110,8 @@ [ { 'comment' => [ '/\*', '\*/'] } # Does not address "line comment" since syntax is target-specific , { 'string' => [ '"', '"', '\\\\.' ] } - , { 'string' => [ "'\\\\?." ] } - , { 'include' => [ '#\s*include', "\$" ] } + , { 'string' => [ "'\\\\?.'" ] } + , { 'include' => [ '#\s*include\b', '$' ] } ] , 'typemap' => { 'd' => 'define' @@ -172,11 +172,11 @@ # bindtextdomain dcgettext dcngettext # --- End of built-in list --- , 'spec' => - [ { 'comment' => [ '#', "\$" ] } + [ { 'comment' => [ '#', '$' ] } , { 'string' => [ '"', '"', '\\\\.' ] } , { 'string' => [ '/', '/', '\\\\.' ] } # for regexps in fact - , { 'include' => [ '@include', "\$" ] } + , { 'include' => [ '@include\b', '$' ] } ] , 'include' => { 'directive' => '(@include)(\s+)(")((?:\\\\.|.)+)(")' @@ -235,10 +235,10 @@ ) ] , 'spec' => [ { 'comment' => [ '/\*', '\*/'] } - , { 'comment' => [ '//', "\$" ] } + , { 'comment' => [ '//', '$' ] } , { 'string' => [ '"', '"', '\\\\.' ] } , { 'string' => [ "'", "'", "\\\\." ] } - , { 'include' => [ '#\s*include', "\$" ] } + , { 'include' => [ '#\s*include\b', '$' ] } ] , 'typemap' => { 'c' => 'class' @@ -293,10 +293,10 @@ ) ] , 'spec' => [ { 'comment' => [ '/\*', '\*/'] } - , { 'comment' => [ '//', "\$" ] } + , { 'comment' => [ '//', '$' ] } , { 'string' => [ '"', '"', '\\\\.' ] } , { 'string' => [ "'", "'", "\\\\." ] } - , { 'include' => [ '#\s*include', "\$" ] } + , { 'include' => [ '#\s*include\b', '$' ] } ] , 'typemap' => { 'c' => 'class' @@ -471,7 +471,7 @@ ZERO ZEROES ZEROS ) ] , 'spec' => - [ { 'comment' => [ '^[\d ]*\*', '$' ] } + [ { 'comment' => [ '^[\d ]*\\*', '$' ] } , { 'string' => [ '"', '"' ] } ] , 'typemap' => @@ -592,7 +592,7 @@ } , 'HTML' => # HTML 4.01 only - { 'identdef' => '[a-zA-Z][\w]*' + { 'identdef' => '[a-zA-Z]\w*' , 'flags' => [ 'case_insensitive' ] , 'reserved' => [ qw( a abbr acronym address applet @@ -628,19 +628,12 @@ [ { 'comment' => [ '<!--', '-->'] } , { 'string' => [ '"', '"' ] } , { 'string' => [ "'", "'" ] } - , { 'include' => [ '(?:href|longdesc|src)="', '"' ] } - , { 'include' => [ "(?:href|longdesc|src)='", "'" ] } + , { 'include' => [ '\b(?:href|longdesc|src)="', '"' ] } + , { 'include' => [ "\b(?:href|longdesc|src)='", "'" ] } # The next one for HTML character entity, but UNSAFE # because & can be found in unprotected query strings - , { 'string' => [ "&", ";" ] } + , { 'string' => [ '&', ';' ] } ] - , 'include' => - { 'directive' => '(\w+=)()("|\')(.+)("|\')' - , 'global' => [ '"', '"' - , '"', '"', ''', "'" - , '(?i)"', '"', '(?i)'', "'" - ] - } , 'typemap' => { 'a' => 'named anchor' , 'f' => 'JavaScript function' @@ -676,11 +669,11 @@ )] , 'spec' => [ { 'comment' => [ '/\*', '\*/'] } - , { 'comment' => [ '//', "\$" ] } + , { 'comment' => [ '//', '$' ] } , { 'string' => [ '"', '"', '\\\\.' ] } , { 'string' => [ "'", "'", "\\\\." ] } - , { 'include' => [ 'import', ";" ] } - , { 'include' => [ 'package', ";" ] } + , { 'include' => [ '\bimport\b', ';' ] } + , { 'include' => [ '\bpackage\b', ';' ] } ] , 'typemap' => { 'c' => 'class' @@ -728,7 +721,7 @@ ) ] , 'spec' => [ { 'comment' => [ '/\*', '\*/'] } - , { 'comment' => [ '//', "\$" ] } + , { 'comment' => [ '//', '$' ] } , { 'string' => [ '"', '"', '\\\\.' ] } , { 'string' => [ "'", "'", "\\\\." ] } ] @@ -784,10 +777,10 @@ call eval value ) ] , 'spec' => - [ { 'comment' => [ '#', "\$"] } + [ { 'comment' => [ '#', '$'] } , { 'string' => [ '"', '"' ] } , { 'string' => [ "'", "'" ] } - , { 'include' => [ '[s-]?include\s', '\$'] } + , { 'include' => [ '(\bs|-)?include\s', '$'] } ] # Multiple inclusion is handled in the specific parser. , 'typemap' => { 'm' => 'macro' } @@ -847,12 +840,8 @@ , { 'comment' => [ '\\(\\*', '\\*\\)' ] } , { 'comment' => [ '//', '$' ] } , { 'string' => [ "'", "'" ] } - , { 'include' => [ 'uses', ';' ] } + , { 'include' => [ '\buses\b', ';' ] } ] - , 'include' => - { 'directive' => '([\w]+)(\s+)()([\w]+)()' - , 'post' => [ '\$', '.pas' ] - } , 'typemap' => { 'f' => 'function' , 'p' => 'procedure' @@ -952,31 +941,33 @@ [ { 'atom' => '(?:\$#?\w+' .'|\\\\.' .'|\b(s|tr|y)\b\s*' - .'(?:(?:\{(?:\\\\.|.)*?\}){2}' - .'|(?:\[(?:\\\\.|.)*?\]}){2}' - .'|(?:\((?:\\\\.|.)*?\)){2}' - .'|(?:\<(?:\\\\.|.)*?\>){2}' + .'(?:(?:\\{(?:\\\\.|.)*?\\}){2}' + .'| (?:\\[(?:\\\\.|.)*?\\]}){2}' + .'| (?:\\((?:\\\\.|.)*?\\)){2}' + .'| (?:\\<(?:\\\\.|.)*?\\>){2}' .'|(.)(?:(?:\\\\.|.)*?\g{-1}){2}' .')' .'|\b(q[qrwx]?|m)\b\s*' - .'(?:\{(?:\\\\.|.)*?\}' - .'|\[(?:\\\\.|.)*?\]' - .'|\((?:\\\\.|.)*?\)' - .'|\<(?:\\\\.|.)*?\>' - .'|(.)(?:\\\\.|.)*?\g{-1}' + .'(?:\\{(?:\\\\.|.)*?\\}' + .'| \\[(?:\\\\.|.)*?\\]' + .'| \\((?:\\\\.|.)*?\\)' + .'| \\<(?:\\\\.|.)*?\\>' + .'|(.)(?:\\\\.|.)*?\\g{-1}' .')' .')' } # NOTE: This complicated 'atom' is an attempt not to lose control # through quote and regexp operators. It is not 100% # bullet-proof. It can't handle nested m{ {...} } for instance. + # NOTE 2: It does not work if the regular expressions and/or replacements + # extend on several lines (as is frequently the case with /x modifier. , { 'include' => ['\buse\s+', ';'] } , { 'include' => ['\brequire\s+', ';'] } , { 'string' => ['"', '"', '\\\\.'] } , { 'string' => ["'", "'", "\\\\."] } , { 'string' => ['\\`', '\\`', '\\\\.'] } - , { 'comment' => ['#', "\$"] } - , { 'comment' => ["^=\\w+", "^=cut"] } + , { 'comment' => ['#', '$'] } + , { 'comment' => ['^=\w+', '^=cut'] } ] # The following include rules are more efficiently implemented # in the Perl.pm module. They are shown as an example of @@ -1056,17 +1047,17 @@ self parent ) ] , 'spec' => - [ { 'comment' => [ '/\\*', '\*/' ] } - , { 'comment' => [ '//', "\$" ] } - , { 'comment' => [ '#', "\$" ] } + [ { 'comment' => [ '/\*', '\*/' ] } + , { 'comment' => [ '//', '$' ] } + , { 'comment' => [ '#', '$' ] } # TODO: Heredoc and Nowdoc if it makes sense # to consider them comments , { 'string' => [ '"', '"', '\\\\.' ] } , { 'string' => [ "'", "'", '\\\\.' ] } - , { 'include' => [ 'require', "\$" ] } - , { 'include' => [ 'include', "\$" ] } - , { 'include' => [ 'require_once', "\$" ] } - , { 'include' => [ 'include_once', "\$" ] } + , { 'include' => [ '\brequire\b', '$' ] } + , { 'include' => [ '\binclude\b', '$' ] } + , { 'include' => [ '\brequire_once\b', '$' ] } + , { 'include' => [ '\binclude_once\b', '$' ] } ], , 'include' => { 'directive' => '([\w]+)(\s*)(\\(\\s*[\'"])([^\'"]+)("\\s*\\))' @@ -1104,13 +1095,13 @@ yield ) ] , 'spec' => - [ { 'comment' => [ '#', "\$" ] } + [ { 'comment' => [ '#', '$' ] } , { 'string' => [ '"""', '"""', '\\\\.' ] } , { 'string' => [ "'''", "'''", "\\\\." ] } , { 'string' => [ '"', '"', '\\\\.' ] } , { 'string' => [ "'", "'", "\\\\." ] } - , { 'include' => [ '\bimport\b', "\$" ] } - , { 'include' => [ '\bfrom\b', "\$" ] } + , { 'include' => [ '\bimport\b', '$' ] } + , { 'include' => [ '\bfrom\b', '$' ] } ] # Include rules implemented in Python.pm to cope with an # endlessly looping case under 'include' patterns. @@ -1156,8 +1147,8 @@ __FILE__ __LINE__ ) ] , 'spec' => - [ { 'comment' => [ '^=begin', '^=end'] } - , { 'comment' => [ '#', "\$"] } + [ { 'comment' => [ '^=begin\b', '^=end\b'] } + , { 'comment' => [ '#', '$'] } , { 'string' => [ '"', '"' , '\\\\(?:(?:[CM]-|c)[^\\\\]?|\$|.)' ] } , { 'string' => [ "'", "'" @@ -1165,17 +1156,16 @@ , { 'string' => [ '\\`', '\\`' , '\\\\(?:(?:[CM]-|c)[^\\\\]?|\$|.)' ] } # The following def does not handle nested construct - , { 'string' => [ '\%[qQrs]?' - . '(?:\\([^(]*?\\)' - . '|\\[[^(]*?\\]' - . '|\\{[^(]*?\\}' - . '|\\<[^(]*?\\>' - . '|([\W]).*?\g{-1}' - . ')' - ] } + , { 'string' => [ '\%[iIqQrswW]?\\(', '\\)', '\\\\.' ] } + , { 'string' => [ '\%[iIqQrswW]?\\[', '\\]', '\\\\.' ] } + , { 'string' => [ '\%[iIqQrswW]?\\{', '\\}', '\\\\.' ] } + , { 'string' => [ '\%[iIqQrswW]?\\<', '\\>', '\\\\.' ] } + , { 'string' => [ '\%[iIqQrswW]?' + . '([\W]).*?\g{-1}' + ] } # , { 'string' => [ "(?<!:):(?:[!%^&*/|+-]|[@$]?[A-Za-z_]+?)", '[A-Za-z_0-9!?=]*(?![A-Za-z_0-9!?=])' ] } - , { 'include' => [ 'require', "\$" ] } - , { 'include' => [ 'load', "\$" ] } + , { 'include' => [ '\brequire\b', '$' ] } + , { 'include' => [ '\bload\b', '$' ] } ] , 'typemap' => { 'c' => 'class' @@ -1376,8 +1366,8 @@ ) ] , 'spec' => [ { 'comment' => [ '/\*', '\*/' ] } - , { 'comment' => [ '//', "\$" ] } - , { 'comment' => [ '--', "\$" ] } + , { 'comment' => [ '//', '$' ] } + , { 'comment' => [ '--', '$' ] } , { 'string' => [ '"', '"', '\\\\.' ] } , { 'string' => [ "'", "'", "\\\\." ] } ] @@ -1563,9 +1553,9 @@ , 'Xor' ] , 'spec' => - [ { 'comment' => [ 'rem ', '\$' ] } + [ { 'comment' => [ '\brem\b', '$' ] } , { 'comment' => [ "'", "\$" ] } - , { 'string' => [ '"', '"', '\\\\.' ] } + , { 'string' => [ '"', '"', '\\\\.' ] } , { 'string' => [ "'", "'", "\\\\." ] } ] , 'typemap' => |
