Merged in ssproessig/pygments-main (pull request #266)

1 files changed, 85 insertions, 49 deletions

diff --git a/pygments/lexers/asm.py b/pygments/lexers/asm.py
index 3f67862c..2727a55d 100644
--- a/pygments/lexers/asm.py
+++ b/pygments/lexers/asm.py
@@ -5,7 +5,7 @@
 
     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.
 """
 
@@ -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):
@@ -216,6 +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),
@@ -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|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
@@ -360,11 +382,25 @@ 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'
     aliases = ['ca65']