Merge pull request #2383 from larsbrinkhoff/troff

More file extensions for Groff

lib/linguist/heuristics.rb

@@ -295,9 +295,25 @@ module Linguist
         Language["Common Lisp"]
       elsif /^(%[%{}]xs|<.*>)/.match(data)
         Language["Lex"]
-      elsif /^\.[a-z][a-z](\s|$)/.match(data)
+      elsif /^\.[a-z][a-z](\s|$)/i.match(data)
         Language["Groff"]
       end
     end
+
+    disambiguate "Groff", "Nemerle" do |data|
+      if /^[.']/.match(data)
+        Language["Groff"]
+      elsif /^(module|namespace|using)\s/.match(data)
+        Language["Nemerle"]
+      end
+    end
+
+    disambiguate "GAS", "Groff" do |data|
+      if /^[.'][a-z][a-z](\s|$)/i.match(data)
+        Language["Groff"]
+      elsif /((^|\s)move?[. ])|\.(include|globa?l)\s/.match(data)
+        Language["GAS"]
+      end
+    end
   end
 end

lib/linguist/languages.yml

@@ -1041,6 +1041,7 @@ GAS:
   group: Assembly
   extensions:
   - .s
+  - .ms
   tm_scope: source.asm.x86
   ace_mode: assembly_x86
 
@@ -1209,13 +1210,26 @@ Groff:
   extensions:
   - .man
   - '.1'
+  - .1in
+  - .1m
+  - .1x
   - '.2'
   - '.3'
+  - .3in
+  - .3m
+  - .3qt
+  - .3x
   - '.4'
   - '.5'
   - '.6'
   - '.7'
+  - '.8'
+  - '.9'
   - .l
+  - .ms
+  - .n
+  - .rno
+  - .roff
   tm_scope: text.groff
   aliases:
   - nroff

samples/GAS/hello.ms

@@ -0,0 +1,91 @@
+# output(): Hello, world.\n
+# mach(): all
+
+# Emit hello world while switching back and forth between arm/thumb.
+# ??? Unfinished
+
+	.macro invalid
+# This is "undefined" but it's not properly decoded yet.
+	.word 0x07ffffff
+# This is stc which isn't recognized yet.
+	stc 0,cr0,[r0]
+	.endm
+
+	.global _start
+_start:
+# Run some simple insns to confirm the engine is at least working.
+	nop
+
+# Skip over output text.
+
+	bl skip_output
+
+hello_text:
+	.asciz "Hello, world.\n"
+
+	.p2align 2
+skip_output:
+
+# Prime loop.
+
+	mov r4, r14
+
+output_next:
+
+# Switch arm->thumb to output next chacter.
+# At this point r4 must point to the next character to output.
+
+	adr r0, into_thumb + 1
+	bx r0
+
+into_thumb:
+	.thumb
+
+# Output a character.
+
+	mov r0,#3 @ writec angel call
+	mov r1,r4
+	swi 0xab @ ??? Confirm number.
+
+# Switch thumb->arm.
+
+	adr r5, back_to_arm
+	bx r5
+
+	.p2align 2
+back_to_arm:
+	.arm
+
+# Load next character, see if done.
+
+	add r4,r4,#1
+	sub r3,r3,r3
+	ldrb r5,[r4,r3]
+	teq r5,#0
+	beq done
+
+# Output a character (in arm mode).
+
+	mov r0,#3
+	mov r1,r4
+	swi #0x123456
+
+# Load next character, see if done.
+
+	add r4,r4,#1
+	sub r3,r3,r3
+	ldrb r5,[r4,r3]
+	teq r5,#0
+	bne output_next
+
+done:
+	mov r0,#0x18
+	ldr r1,exit_code
+	swi #0x123456
+
+# If that fails, try to die with an invalid insn.
+
+	invalid
+
+exit_code:
+	.word 0x20026

samples/Groff/Tcl.n

@@ -0,0 +1,275 @@
+'\"
+'\" Copyright (c) 1993 The Regents of the University of California.
+'\" Copyright (c) 1994-1996 Sun Microsystems, Inc.
+'\"
+'\" See the file "license.terms" for information on usage and redistribution
+'\" of this file, and for a DISCLAIMER OF ALL WARRANTIES.
+'\"
+.TH Tcl n "8.6" Tcl "Tcl Built-In Commands"
+.so man.macros
+.BS
+.SH NAME
+Tcl \- Tool Command Language
+.SH SYNOPSIS
+Summary of Tcl language syntax.
+.BE
+.SH DESCRIPTION
+.PP
+The following rules define the syntax and semantics of the Tcl language:
+.IP "[1] \fBCommands.\fR"
+A Tcl script is a string containing one or more commands.
+Semi-colons and newlines are command separators unless quoted as
+described below.
+Close brackets are command terminators during command substitution
+(see below) unless quoted.
+.IP "[2] \fBEvaluation.\fR"
+A command is evaluated in two steps.
+First, the Tcl interpreter breaks the command into \fIwords\fR
+and performs substitutions as described below.
+These substitutions are performed in the same way for all
+commands.
+Secondly, the first word is used to locate a command procedure to
+carry out the command, then all of the words of the command are
+passed to the command procedure.
+The command procedure is free to interpret each of its words
+in any way it likes, such as an integer, variable name, list,
+or Tcl script.
+Different commands interpret their words differently.
+.IP "[3] \fBWords.\fR"
+Words of a command are separated by white space (except for
+newlines, which are command separators).
+.IP "[4] \fBDouble quotes.\fR"
+If the first character of a word is double-quote
+.PQ \N'34'
+then the word is terminated by the next double-quote character.
+If semi-colons, close brackets, or white space characters
+(including newlines) appear between the quotes then they are treated
+as ordinary characters and included in the word.
+Command substitution, variable substitution, and backslash substitution
+are performed on the characters between the quotes as described below.
+The double-quotes are not retained as part of the word.
+.IP "[5] \fBArgument expansion.\fR"
+If a word starts with the string
+.QW {*}
+followed by a non-whitespace character, then the leading
+.QW {*}
+is removed and the rest of the word is parsed and substituted as any other
+word. After substitution, the word is parsed as a list (without command or
+variable substitutions; backslash substitutions are performed as is normal for
+a list and individual internal words may be surrounded by either braces or
+double-quote characters), and its words are added to the command being
+substituted. For instance,
+.QW "cmd a {*}{b [c]} d {*}{$e f {g h}}"
+is equivalent to
+.QW "cmd a b {[c]} d {$e} f {g h}" .
+.IP "[6] \fBBraces.\fR"
+If the first character of a word is an open brace
+.PQ {
+and rule [5] does not apply, then
+the word is terminated by the matching close brace
+.PQ } "" .
+Braces nest within the word: for each additional open
+brace there must be an additional close brace (however,
+if an open brace or close brace within the word is
+quoted with a backslash then it is not counted in locating the
+matching close brace).
+No substitutions are performed on the characters between the
+braces except for backslash-newline substitutions described
+below, nor do semi-colons, newlines, close brackets,
+or white space receive any special interpretation.
+The word will consist of exactly the characters between the
+outer braces, not including the braces themselves.
+.IP "[7] \fBCommand substitution.\fR"
+If a word contains an open bracket
+.PQ [
+then Tcl performs \fIcommand substitution\fR.
+To do this it invokes the Tcl interpreter recursively to process
+the characters following the open bracket as a Tcl script.
+The script may contain any number of commands and must be terminated
+by a close bracket
+.PQ ] "" .
+The result of the script (i.e. the result of its last command) is
+substituted into the word in place of the brackets and all of the
+characters between them.
+There may be any number of command substitutions in a single word.
+Command substitution is not performed on words enclosed in braces.
+.IP "[8] \fBVariable substitution.\fR"
+If a word contains a dollar-sign
+.PQ $
+followed by one of the forms
+described below, then Tcl performs \fIvariable
+substitution\fR:  the dollar-sign and the following characters are
+replaced in the word by the value of a variable.
+Variable substitution may take any of the following forms:
+.RS
+.TP 15
+\fB$\fIname\fR
+.
+\fIName\fR is the name of a scalar variable;  the name is a sequence
+of one or more characters that are a letter, digit, underscore,
+or namespace separators (two or more colons).
+Letters and digits are \fIonly\fR the standard ASCII ones (\fB0\fR\(en\fB9\fR,
+\fBA\fR\(en\fBZ\fR and \fBa\fR\(en\fBz\fR).
+.TP 15
+\fB$\fIname\fB(\fIindex\fB)\fR
+.
+\fIName\fR gives the name of an array variable and \fIindex\fR gives
+the name of an element within that array.
+\fIName\fR must contain only letters, digits, underscores, and
+namespace separators, and may be an empty string.
+Letters and digits are \fIonly\fR the standard ASCII ones (\fB0\fR\(en\fB9\fR,
+\fBA\fR\(en\fBZ\fR and \fBa\fR\(en\fBz\fR).
+Command substitutions, variable substitutions, and backslash
+substitutions are performed on the characters of \fIindex\fR.
+.TP 15
+\fB${\fIname\fB}\fR
+.
+\fIName\fR is the name of a scalar variable or array element.  It may contain
+any characters whatsoever except for close braces.  It indicates an array
+element if \fIname\fR is in the form
+.QW \fIarrayName\fB(\fIindex\fB)\fR
+where \fIarrayName\fR does not contain any open parenthesis characters,
+.QW \fB(\fR ,
+or close brace characters,
+.QW \fB}\fR ,
+and \fIindex\fR can be any sequence of characters except for close brace
+characters.  No further
+substitutions are performed during the parsing of \fIname\fR.
+.PP
+There may be any number of variable substitutions in a single word.
+Variable substitution is not performed on words enclosed in braces.
+.PP
+Note that variables may contain character sequences other than those listed
+above, but in that case other mechanisms must be used to access them (e.g.,
+via the \fBset\fR command's single-argument form).
+.RE
+.IP "[9] \fBBackslash substitution.\fR"
+If a backslash
+.PQ \e
+appears within a word then \fIbackslash substitution\fR occurs.
+In all cases but those described below the backslash is dropped and
+the following character is treated as an ordinary
+character and included in the word.
+This allows characters such as double quotes, close brackets,
+and dollar signs to be included in words without triggering
+special processing.
+The following table lists the backslash sequences that are
+handled specially, along with the value that replaces each sequence.
+.RS
+.TP 7
+\e\fBa\fR
+Audible alert (bell) (Unicode U+000007).
+.TP 7
+\e\fBb\fR
+Backspace (Unicode U+000008).
+.TP 7
+\e\fBf\fR
+Form feed (Unicode U+00000C).
+.TP 7
+\e\fBn\fR
+Newline (Unicode U+00000A).
+.TP 7
+\e\fBr\fR
+Carriage-return (Unicode U+00000D).
+.TP 7
+\e\fBt\fR
+Tab (Unicode U+000009).
+.TP 7
+\e\fBv\fR
+Vertical tab (Unicode U+00000B).
+.TP 7
+\e\fB<newline>\fIwhiteSpace\fR
+.
+A single space character replaces the backslash, newline, and all spaces
+and tabs after the newline.  This backslash sequence is unique in that it
+is replaced in a separate pre-pass before the command is actually parsed.
+This means that it will be replaced even when it occurs between braces,
+and the resulting space will be treated as a word separator if it is not
+in braces or quotes.
+.TP 7
+\e\e
+Backslash
+.PQ \e "" .
+.TP 7
+\e\fIooo\fR 
+.
+The digits \fIooo\fR (one, two, or three of them) give a eight-bit octal 
+value for the Unicode character that will be inserted, in the range
+\fI000\fR\(en\fI377\fR (i.e., the range U+000000\(enU+0000FF).
+The parser will stop just before this range overflows, or when
+the maximum of three digits is reached.  The upper bits of the Unicode
+character will be 0.
+.TP 7
+\e\fBx\fIhh\fR 
+.
+The hexadecimal digits \fIhh\fR (one or two of them) give an eight-bit
+hexadecimal value for the Unicode character that will be inserted.  The upper
+bits of the Unicode character will be 0 (i.e., the character will be in the
+range U+000000\(enU+0000FF).
+.TP 7
+\e\fBu\fIhhhh\fR 
+.
+The hexadecimal digits \fIhhhh\fR (one, two, three, or four of them) give a
+sixteen-bit hexadecimal value for the Unicode character that will be
+inserted.  The upper bits of the Unicode character will be 0 (i.e., the
+character will be in the range U+000000\(enU+00FFFF).
+.TP 7
+\e\fBU\fIhhhhhhhh\fR 
+.
+The hexadecimal digits \fIhhhhhhhh\fR (one up to eight of them) give a
+twenty-one-bit hexadecimal value for the Unicode character that will be
+inserted, in the range U+000000\(enU+10FFFF.  The parser will stop just
+before this range overflows, or when the maximum of eight digits
+is reached.  The upper bits of the Unicode character will be 0.
+.RS
+.PP
+The range U+010000\(enU+10FFFD is reserved for the future.
+.RE
+.PP
+Backslash substitution is not performed on words enclosed in braces,
+except for backslash-newline as described above.
+.RE
+.IP "[10] \fBComments.\fR"
+If a hash character
+.PQ #
+appears at a point where Tcl is
+expecting the first character of the first word of a command,
+then the hash character and the characters that follow it, up
+through the next newline, are treated as a comment and ignored.
+The comment character only has significance when it appears
+at the beginning of a command.
+.IP "[11] \fBOrder of substitution.\fR"
+Each character is processed exactly once by the Tcl interpreter
+as part of creating the words of a command.
+For example, if variable substitution occurs then no further
+substitutions are performed on the value of the variable;  the
+value is inserted into the word verbatim.
+If command substitution occurs then the nested command is
+processed entirely by the recursive call to the Tcl interpreter;
+no substitutions are performed before making the recursive
+call and no additional substitutions are performed on the result
+of the nested script.
+.RS
+.PP
+Substitutions take place from left to right, and each substitution is
+evaluated completely before attempting to evaluate the next.  Thus, a
+sequence like
+.PP
+.CS
+set y [set x 0][incr x][incr x]
+.CE
+.PP
+will always set the variable \fIy\fR to the value, \fI012\fR.
+.RE
+.IP "[12] \fBSubstitution and word boundaries.\fR"
+Substitutions do not affect the word boundaries of a command,
+except for argument expansion as specified in rule [5].
+For example, during variable substitution the entire value of
+the variable becomes part of a single word, even if the variable's
+value contains spaces.
+.SH KEYWORDS
+backslash, command, comment, script, substitution, variable
+'\" Local Variables:
+'\" mode: nroff
+'\" fill-column: 78
+'\" End: