diff options
Diffstat (limited to 'pygments/lexers/asm.py')
| -rw-r--r-- | pygments/lexers/asm.py | 117 |
1 files changed, 77 insertions, 40 deletions
diff --git a/pygments/lexers/asm.py b/pygments/lexers/asm.py index 7ff64bcc..f16dbadd 100644 --- a/pygments/lexers/asm.py +++ b/pygments/lexers/asm.py @@ -5,19 +5,21 @@ Lexers for assembly languages. - :copyright: Copyright 2006-2013 by the Pygments team, see AUTHORS. + :copyright: Copyright 2006-2014 by the Pygments team, see AUTHORS. :license: BSD, see LICENSE for details. """ import re from pygments.lexer import RegexLexer, include, bygroups, using, DelegatingLexer -from pygments.lexers.compiled import DLexer, CppLexer, CLexer +from pygments.lexers.c_cpp import CppLexer, CLexer +from pygments.lexers.d import DLexer from pygments.token import Text, Name, Number, String, Comment, Punctuation, \ - Other, Keyword, Operator + Other, Keyword, Operator -__all__ = ['GasLexer', 'ObjdumpLexer','DObjdumpLexer', 'CppObjdumpLexer', - 'CObjdumpLexer', 'LlvmLexer', 'NasmLexer', 'Ca65Lexer'] +__all__ = ['GasLexer', 'ObjdumpLexer', 'DObjdumpLexer', 'CppObjdumpLexer', + 'CObjdumpLexer', 'LlvmLexer', 'NasmLexer', 'NasmObjdumpLexer', + 'Ca65Lexer'] class GasLexer(RegexLexer): @@ -25,7 +27,7 @@ class GasLexer(RegexLexer): For Gas (AT&T) assembly code. """ name = 'GAS' - aliases = ['gas'] + aliases = ['gas', 'asm'] filenames = ['*.s', '*.S'] mimetypes = ['text/x-gas'] @@ -96,18 +98,12 @@ class GasLexer(RegexLexer): return 0.1 -class ObjdumpLexer(RegexLexer): +def _objdump_lexer_tokens(asm_lexer): """ - For the output of 'objdump -dr' + Common objdump lexer tokens to wrap an ASM lexer. """ - name = 'objdump' - aliases = ['objdump'] - filenames = ['*.objdump'] - mimetypes = ['text/x-objdump'] - - hex = r'[0-9A-Za-z]' - - tokens = { + hex_re = r'[0-9A-Za-z]' + return { 'root': [ # File name & format: ('(.*?)(:)( +file format )(.*?)$', @@ -117,33 +113,33 @@ class ObjdumpLexer(RegexLexer): bygroups(Text, Name.Label, Punctuation)), # Function labels # (With offset) - ('('+hex+'+)( )(<)(.*?)([-+])(0[xX][A-Za-z0-9]+)(>:)$', + ('('+hex_re+'+)( )(<)(.*?)([-+])(0[xX][A-Za-z0-9]+)(>:)$', bygroups(Number.Hex, Text, Punctuation, Name.Function, Punctuation, Number.Hex, Punctuation)), # (Without offset) - ('('+hex+'+)( )(<)(.*?)(>:)$', + ('('+hex_re+'+)( )(<)(.*?)(>:)$', bygroups(Number.Hex, Text, Punctuation, Name.Function, Punctuation)), # Code line with disassembled instructions - ('( *)('+hex+r'+:)(\t)((?:'+hex+hex+' )+)( *\t)([a-zA-Z].*?)$', + ('( *)('+hex_re+r'+:)(\t)((?:'+hex_re+hex_re+' )+)( *\t)([a-zA-Z].*?)$', bygroups(Text, Name.Label, Text, Number.Hex, Text, - using(GasLexer))), + using(asm_lexer))), # Code line with ascii - ('( *)('+hex+r'+:)(\t)((?:'+hex+hex+' )+)( *)(.*?)$', + ('( *)('+hex_re+r'+:)(\t)((?:'+hex_re+hex_re+' )+)( *)(.*?)$', bygroups(Text, Name.Label, Text, Number.Hex, Text, String)), # Continued code line, only raw opcodes without disassembled # instruction - ('( *)('+hex+r'+:)(\t)((?:'+hex+hex+' )+)$', + ('( *)('+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+r'+:)( )([^\t]+)(\t)(.*?)([-+])(0x' + hex + '+)$', + (r'(\t\t\t)('+hex_re+r'+:)( )([^\t]+)(\t)(.*?)([-+])(0x'+hex_re+'+)$', bygroups(Text, Name.Label, Text, Name.Property, Text, Name.Constant, Punctuation, Number.Hex)), # (Without offset) - (r'(\t\t\t)('+hex+r'+:)( )([^\t]+)(\t)(.*?)$', + (r'(\t\t\t)('+hex_re+r'+:)( )([^\t]+)(\t)(.*?)$', bygroups(Text, Name.Label, Text, Name.Property, Text, Name.Constant)), (r'[^\n]+\n', Other) @@ -151,6 +147,18 @@ class ObjdumpLexer(RegexLexer): } +class ObjdumpLexer(RegexLexer): + """ + For the output of 'objdump -dr' + """ + name = 'objdump' + aliases = ['objdump'] + filenames = ['*.objdump'] + mimetypes = ['text/x-objdump'] + + tokens = _objdump_lexer_tokens(GasLexer) + + class DObjdumpLexer(DelegatingLexer): """ For the output of 'objdump -Sr on compiled D files' @@ -212,10 +220,11 @@ class LlvmLexer(RegexLexer): include('keyword'), - (r'%' + identifier, Name.Variable),#Name.Identifier.Local), - (r'@' + identifier, Name.Variable.Global),#Name.Identifier.Global), - (r'%\d+', Name.Variable.Anonymous),#Name.Identifier.Anonymous), - (r'@\d+', Name.Variable.Global),#Name.Identifier.Anonymous), + (r'%' + identifier, Name.Variable), + (r'@' + identifier, Name.Variable.Global), + (r'%\d+', Name.Variable.Anonymous), + (r'@\d+', Name.Variable.Global), + (r'#\d+', Name.Variable.Global), (r'!' + identifier, Name.Variable), (r'!\d+', Name.Variable.Anonymous), (r'c?' + string, String), @@ -242,17 +251,24 @@ class LlvmLexer(RegexLexer): r'|thread_local|zeroinitializer|undef|null|to|tail|target|triple' r'|datalayout|volatile|nuw|nsw|nnan|ninf|nsz|arcp|fast|exact|inbounds' r'|align|addrspace|section|alias|module|asm|sideeffect|gc|dbg' + r'|linker_private_weak' + r'|attributes|blockaddress|initialexec|localdynamic|localexec' + r'|prefix|unnamed_addr' r'|ccc|fastcc|coldcc|x86_stdcallcc|x86_fastcallcc|arm_apcscc' - r'|arm_aapcscc|arm_aapcs_vfpcc' + r'|arm_aapcscc|arm_aapcs_vfpcc|ptx_device|ptx_kernel' + r'|intel_ocl_bicc|msp430_intrcc|spir_func|spir_kernel' + r'|x86_64_sysvcc|x86_64_win64cc|x86_thiscallcc' r'|cc|c' r'|signext|zeroext|inreg|sret|nounwind|noreturn|noalias|nocapture' r'|byval|nest|readnone|readonly' - r'|inlinehint|noinline|alwaysinline|optsize|ssp|sspreq|noredzone' r'|noimplicitfloat|naked' + r'|builtin|cold|nobuiltin|noduplicate|nonlazybind|optnone' + r'|returns_twice|sanitize_address|sanitize_memory|sanitize_thread' + r'|sspstrong|uwtable|returned' r'|type|opaque' @@ -261,24 +277,30 @@ class LlvmLexer(RegexLexer): r'|oeq|one|olt|ogt|ole' r'|oge|ord|uno|ueq|une' r'|x' + r'|acq_rel|acquire|alignstack|atomic|catch|cleanup|filter' + r'|inteldialect|max|min|monotonic|nand|personality|release' + r'|seq_cst|singlethread|umax|umin|unordered|xchg' # instructions r'|add|fadd|sub|fsub|mul|fmul|udiv|sdiv|fdiv|urem|srem|frem|shl' r'|lshr|ashr|and|or|xor|icmp|fcmp' r'|phi|call|trunc|zext|sext|fptrunc|fpext|uitofp|sitofp|fptoui' - r'fptosi|inttoptr|ptrtoint|bitcast|select|va_arg|ret|br|switch' + r'|fptosi|inttoptr|ptrtoint|bitcast|select|va_arg|ret|br|switch' r'|invoke|unwind|unreachable' + r'|indirectbr|landingpad|resume' r'|malloc|alloca|free|load|store|getelementptr' r'|extractelement|insertelement|shufflevector|getresult' r'|extractvalue|insertvalue' + r'|atomicrmw|cmpxchg|fence' + r')\b', Keyword), # Types - (r'void|float|double|x86_fp80|fp128|ppc_fp128|label|metadata', + (r'void|half|float|double|x86_fp80|fp128|ppc_fp128|label|metadata', Keyword.Type), # Integer types @@ -296,8 +318,8 @@ class NasmLexer(RegexLexer): filenames = ['*.asm', '*.ASM'] mimetypes = ['text/x-nasm'] - identifier = r'[a-zA-Z$._?][a-zA-Z0-9$._?#@~]*' - hexn = r'(?:0[xX][0-9a-fA-F]+|$0[0-9a-fA-F]*|[0-9]+[0-9a-fA-F]*h)' + identifier = r'[a-z$._?][\w$.?#@~]*' + hexn = r'(?:0[xX][0-9a-f]+|$0[0-9a-f]*|[0-9]+[0-9a-f]*h)' octn = r'[0-7]+q' binn = r'[01]+b' decn = r'[0-9]+' @@ -331,7 +353,7 @@ class NasmLexer(RegexLexer): (string, String), (hexn, Number.Hex), (octn, Number.Oct), - (binn, Number), + (binn, Number.Bin), (floatn, Number.Float), (decn, Number.Integer), include('punctuation'), @@ -360,13 +382,27 @@ class NasmLexer(RegexLexer): } +class NasmObjdumpLexer(ObjdumpLexer): + """ + For the output of 'objdump -d -M intel'. + + .. versionadded:: 2.0 + """ + name = 'objdump-nasm' + aliases = ['objdump-nasm'] + filenames = ['*.objdump-intel'] + mimetypes = ['text/x-nasm-objdump'] + + tokens = _objdump_lexer_tokens(NasmLexer) + + class Ca65Lexer(RegexLexer): """ For ca65 assembler sources. - *New in Pygments 1.6.* + .. versionadded:: 1.6 """ - name = 'ca65' + name = 'ca65 assembler' aliases = ['ca65'] filenames = ['*.s'] @@ -381,13 +417,14 @@ class Ca65Lexer(RegexLexer): r'|cl[cvdi]|se[cdi]|jmp|jsr|bne|beq|bpl|bmi|bvc|bvs|bcc|bcs' r'|p[lh][ap]|rt[is]|brk|nop|ta[xy]|t[xy]a|txs|tsx|and|ora|eor' r'|bit)\b', Keyword), - (r'\.[a-z0-9_]+', Keyword.Pseudo), + (r'\.\w+', Keyword.Pseudo), (r'[-+~*/^&|!<>=]', Operator), (r'"[^"\n]*.', String), (r"'[^'\n]*.", String.Char), (r'\$[0-9a-f]+|[0-9a-f]+h\b', Number.Hex), - (r'\d+|%[01]+', Number.Integer), - (r'[#,.:()=]', Punctuation), + (r'\d+', Number.Integer), + (r'%[01]+', Number.Bin), + (r'[#,.:()=\[\]]', Punctuation), (r'[a-z_.@$][\w.@$]*', Name), ] } |