diff options
Diffstat (limited to 'pygments/lexers/asm.py')
| -rw-r--r-- | pygments/lexers/asm.py | 151 |
1 files changed, 116 insertions, 35 deletions
diff --git a/pygments/lexers/asm.py b/pygments/lexers/asm.py index 4740569c..fc361e2f 100644 --- a/pygments/lexers/asm.py +++ b/pygments/lexers/asm.py @@ -5,7 +5,7 @@ Lexers for assembly languages. - :copyright: Copyright 2006-2010 by the Pygments team, see AUTHORS. + :copyright: Copyright 2006-2014 by the Pygments team, see AUTHORS. :license: BSD, see LICENSE for details. """ @@ -13,10 +13,11 @@ import re from pygments.lexer import RegexLexer, include, bygroups, using, DelegatingLexer from pygments.lexers.compiled import DLexer, CppLexer, CLexer -from pygments.token import * +from pygments.token import Text, Name, Number, String, Comment, Punctuation, \ + Other, Keyword, Operator __all__ = ['GasLexer', 'ObjdumpLexer','DObjdumpLexer', 'CppObjdumpLexer', - 'CObjdumpLexer', 'LlvmLexer', 'NasmLexer'] + 'CObjdumpLexer', 'LlvmLexer', 'NasmLexer', 'NasmObjdumpLexer', 'Ca65Lexer'] class GasLexer(RegexLexer): @@ -24,13 +25,13 @@ class GasLexer(RegexLexer): For Gas (AT&T) assembly code. """ name = 'GAS' - aliases = ['gas'] + aliases = ['gas', 'asm'] filenames = ['*.s', '*.S'] mimetypes = ['text/x-gas'] #: optional Comment or Whitespace string = r'"(\\"|[^"])*"' - char = r'[a-zA-Z$._0-9@]' + char = r'[a-zA-Z$._0-9@-]' identifier = r'(?:[a-zA-Z$_]' + char + '*|\.' + char + '+)' number = r'(?:0[xX][a-zA-Z0-9]+|\d+)' @@ -72,6 +73,7 @@ class GasLexer(RegexLexer): ('%' + identifier, Name.Variable), # Numeric constants ('$'+number, Number.Integer), + (r"$'(.|\\')'", String.Char), (r'[\r\n]+', Text, '#pop'), (r'#.*?$', Comment, '#pop'), include('punctuation'), @@ -88,20 +90,18 @@ class GasLexer(RegexLexer): } def analyse_text(text): - return re.match(r'^\.\w+', text, re.M) + if re.match(r'^\.(text|data|section)', text, re.M): + return True + elif re.match(r'^\.\w+', text, re.M): + 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 )(.*?)$', @@ -111,40 +111,54 @@ class ObjdumpLexer(RegexLexer): bygroups(Text, Name.Label, Punctuation)), # Function labels # (With offset) - ('('+hex+'+)( )(<)(.*?)([-+])(0[xX][A-Za-z0-9]+)(>:)$', + ('('+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+' )+)$', bygroups(Text, Name.Label, Text, Number.Hex)), # Skipped a few bytes - ('\t\.\.\.$', Text), + (r'\t\.\.\.$', Text), # Relocation line # (With offset) - ('(\t\t\t)('+hex+'+:)( )([^\t]+)(\t)(.*?)([-+])(0x' + hex + '+)$', + (r'(\t\t\t)('+hex_re+r'+:)( )([^\t]+)(\t)(.*?)([-+])(0x'+hex_re+'+)$', bygroups(Text, Name.Label, Text, Name.Property, Text, Name.Constant, Punctuation, Number.Hex)), # (Without offset) - ('(\t\t\t)('+hex+'+:)( )([^\t]+)(\t)(.*?)$', + (r'(\t\t\t)('+hex_re+r'+:)( )([^\t]+)(\t)(.*?)$', bygroups(Text, Name.Label, Text, Name.Property, Text, Name.Constant)), - ('[^\n]+\n', Other) + (r'[^\n]+\n', Other) ] } +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' @@ -202,7 +216,7 @@ class LlvmLexer(RegexLexer): include('whitespace'), # Before keywords, because keywords are valid label names :(... - (r'^\s*' + identifier + '\s*:', Name.Label), + (identifier + '\s*:', Name.Label), include('keyword'), @@ -210,6 +224,7 @@ class LlvmLexer(RegexLexer): (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'#\d+', Name.Variable.Global),#Name.Identifier.Global), (r'!' + identifier, Name.Variable), (r'!\d+', Name.Variable.Anonymous), (r'c?' + string, String), @@ -234,19 +249,26 @@ class LlvmLexer(RegexLexer): r'|linkonce_odr|weak|weak_odr|appending|dllimport|dllexport' r'|common|default|hidden|protected|extern_weak|external' r'|thread_local|zeroinitializer|undef|null|to|tail|target|triple' - r'|deplibs|datalayout|volatile|nuw|nsw|exact|inbounds|align' - r'|addrspace|section|alias|module|asm|sideeffect|gc|dbg' + 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' @@ -255,24 +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 @@ -296,9 +324,10 @@ class NasmLexer(RegexLexer): binn = r'[01]+b' decn = r'[0-9]+' floatn = decn + r'\.e?' + decn - string = r'"(\\"|[^"])*"|' + r"'(\\'|[^'])*'" + string = r'"(\\"|[^"\n])*"|' + r"'(\\'|[^'\n])*'|" + r"`(\\`|[^`\n])*`" declkw = r'(?:res|d)[bwdqt]|times' - register = (r'[a-d][lh]|e?[a-d]x|e?[sb]p|e?[sd]i|[c-gs]s|st[0-7]|' + register = (r'r[0-9][0-5]?[bwd]|' + r'[a-d][lh]|[er]?[a-d]x|[er]?[sb]p|[er]?[sd]i|[c-gs]s|st[0-7]|' r'mm[0-7]|cr[0-4]|dr[0-367]|tr[3-7]') wordop = r'seg|wrt|strict' type = r'byte|[dq]?word' @@ -351,3 +380,55 @@ class NasmLexer(RegexLexer): (type, Keyword.Type) ], } + + +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. + + .. versionadded:: 1.6 + """ + name = 'ca65' + aliases = ['ca65'] + filenames = ['*.s'] + + flags = re.IGNORECASE + + tokens = { + 'root': [ + (r';.*', Comment.Single), + (r'\s+', Text), + (r'[a-z_.@$][\w.@$]*:', Name.Label), + (r'((ld|st)[axy]|(in|de)[cxy]|asl|lsr|ro[lr]|adc|sbc|cmp|cp[xy]' + r'|cl[cvdi]|se[cdi]|jmp|jsr|bne|beq|bpl|bmi|bvc|bvs|bcc|bcs' + r'|p[lh][ap]|rt[is]|brk|nop|ta[xy]|t[xy]a|txs|tsx|and|ora|eor' + r'|bit)\b', Keyword), + (r'\.[a-z0-9_]+', Keyword.Pseudo), + (r'[-+~*/^&|!<>=]', Operator), + (r'"[^"\n]*.', String), + (r"'[^'\n]*.", String.Char), + (r'\$[0-9a-f]+|[0-9a-f]+h\b', Number.Hex), + (r'\d+|%[01]+', Number.Integer), + (r'[#,.:()=]', Punctuation), + (r'[a-z_.@$][\w.@$]*', Name), + ] + } + + def analyse_text(self, text): + # comments in GAS start with "#" + if re.match(r'^\s*;', text, re.MULTILINE): + return 0.9 |