diff options
author | Georg Brandl <georg@python.org> | 2014-03-04 15:28:37 +0100 |
---|---|---|
committer | Georg Brandl <georg@python.org> | 2014-03-04 15:28:37 +0100 |
commit | e048d61032829ab7a39089552cf450b37edc0027 (patch) | |
tree | 2f2c6de583983f5b836b2d8c20dfd1b416104ac1 /pygments/lexers/asm.py | |
parent | be67ecf5a68aa7a4b7c6dcaaaa4992343eb2762b (diff) | |
parent | cbaef37f462222fb5d874fa83e83cb8e76ac9f97 (diff) | |
download | pygments-e048d61032829ab7a39089552cf450b37edc0027.tar.gz |
Merged in alkino/pygments-main (pull request #282)
Fix docstring from analyze_text to analyse_text
Diffstat (limited to 'pygments/lexers/asm.py')
-rw-r--r-- | pygments/lexers/asm.py | 107 |
1 files changed, 63 insertions, 44 deletions
diff --git a/pygments/lexers/asm.py b/pygments/lexers/asm.py index 6cdb1134..00056a9e 100644 --- a/pygments/lexers/asm.py +++ b/pygments/lexers/asm.py @@ -17,7 +17,7 @@ from pygments.token import Text, Name, Number, String, Comment, Punctuation, \ Other, Keyword, Operator __all__ = ['GasLexer', 'ObjdumpLexer','DObjdumpLexer', 'CppObjdumpLexer', - 'CObjdumpLexer', 'LlvmLexer', 'NasmLexer', 'Ca65Lexer'] + 'CObjdumpLexer', 'LlvmLexer', 'NasmLexer', 'NasmObjdumpLexer', 'Ca65Lexer'] class GasLexer(RegexLexer): @@ -96,6 +96,55 @@ class GasLexer(RegexLexer): return 0.1 +def _objdump_lexer_tokens(asm_lexer): + """ + Common objdump lexer tokens to wrap an ASM lexer. + """ + hex_re = r'[0-9A-Za-z]' + return { + 'root': [ + # File name & format: + ('(.*?)(:)( +file format )(.*?)$', + bygroups(Name.Label, Punctuation, Text, String)), + # Section header + ('(Disassembly of section )(.*?)(:)$', + bygroups(Text, Name.Label, Punctuation)), + # Function labels + # (With offset) + ('('+hex_re+'+)( )(<)(.*?)([-+])(0[xX][A-Za-z0-9]+)(>:)$', + bygroups(Number.Hex, Text, Punctuation, Name.Function, + Punctuation, Number.Hex, Punctuation)), + # (Without offset) + ('('+hex_re+'+)( )(<)(.*?)(>:)$', + bygroups(Number.Hex, Text, Punctuation, Name.Function, + Punctuation)), + # Code line with disassembled instructions + ('( *)('+hex_re+r'+:)(\t)((?:'+hex_re+hex_re+' )+)( *\t)([a-zA-Z].*?)$', + bygroups(Text, Name.Label, Text, Number.Hex, Text, + using(asm_lexer))), + # Code line with ascii + ('( *)('+hex_re+r'+:)(\t)((?:'+hex_re+hex_re+' )+)( *)(.*?)$', + bygroups(Text, Name.Label, Text, Number.Hex, Text, String)), + # Continued code line, only raw opcodes without disassembled + # instruction + ('( *)('+hex_re+r'+:)(\t)((?:'+hex_re+hex_re+' )+)$', + bygroups(Text, Name.Label, Text, Number.Hex)), + # Skipped a few bytes + (r'\t\.\.\.$', Text), + # Relocation line + # (With offset) + (r'(\t\t\t)('+hex_re+r'+:)( )([^\t]+)(\t)(.*?)([-+])(0x'+hex_re+'+)$', + bygroups(Text, Name.Label, Text, Name.Property, Text, + Name.Constant, Punctuation, Number.Hex)), + # (Without offset) + (r'(\t\t\t)('+hex_re+r'+:)( )([^\t]+)(\t)(.*?)$', + bygroups(Text, Name.Label, Text, Name.Property, Text, + Name.Constant)), + (r'[^\n]+\n', Other) + ] + } + + class ObjdumpLexer(RegexLexer): """ For the output of 'objdump -dr' @@ -105,50 +154,9 @@ class ObjdumpLexer(RegexLexer): filenames = ['*.objdump'] mimetypes = ['text/x-objdump'] - hex = r'[0-9A-Za-z]' - tokens = { - 'root': [ - # File name & format: - ('(.*?)(:)( +file format )(.*?)$', - bygroups(Name.Label, Punctuation, Text, String)), - # Section header - ('(Disassembly of section )(.*?)(:)$', - bygroups(Text, Name.Label, Punctuation)), - # Function labels - # (With offset) - ('('+hex+'+)( )(<)(.*?)([-+])(0[xX][A-Za-z0-9]+)(>:)$', - bygroups(Number.Hex, Text, Punctuation, Name.Function, - Punctuation, Number.Hex, Punctuation)), - # (Without offset) - ('('+hex+'+)( )(<)(.*?)(>:)$', - bygroups(Number.Hex, Text, Punctuation, Name.Function, - Punctuation)), - # Code line with disassembled instructions - ('( *)('+hex+r'+:)(\t)((?:'+hex+hex+' )+)( *\t)([a-zA-Z].*?)$', - bygroups(Text, Name.Label, Text, Number.Hex, Text, - using(GasLexer))), - # Code line with ascii - ('( *)('+hex+r'+:)(\t)((?:'+hex+hex+' )+)( *)(.*?)$', - bygroups(Text, Name.Label, Text, Number.Hex, Text, String)), - # Continued code line, only raw opcodes without disassembled - # instruction - ('( *)('+hex+r'+:)(\t)((?:'+hex+hex+' )+)$', - bygroups(Text, Name.Label, Text, Number.Hex)), - # Skipped a few bytes - (r'\t\.\.\.$', Text), - # Relocation line - # (With offset) - (r'(\t\t\t)('+hex+r'+:)( )([^\t]+)(\t)(.*?)([-+])(0x' + hex + '+)$', - bygroups(Text, Name.Label, Text, Name.Property, Text, - Name.Constant, Punctuation, Number.Hex)), - # (Without offset) - (r'(\t\t\t)('+hex+r'+:)( )([^\t]+)(\t)(.*?)$', - bygroups(Text, Name.Label, Text, Name.Property, Text, - Name.Constant)), - (r'[^\n]+\n', Other) - ] - } + tokens = _objdump_lexer_tokens(GasLexer) + class DObjdumpLexer(DelegatingLexer): @@ -374,6 +382,17 @@ class NasmLexer(RegexLexer): } +class NasmObjdumpLexer(ObjdumpLexer): + """ + For the output of 'objdump -d -M intel' + """ + name = 'objdump-nasm' + aliases = ['objdump-nasm'] + filenames = ['*.objdump-intel'] + + tokens = _objdump_lexer_tokens(NasmLexer) + + class Ca65Lexer(RegexLexer): """ For ca65 assembler sources. |