Add Asciidoc filetype

Add a filetype for Asciidoc with symbol parser, but not styling.

data/filetype_extensions.conf

@@ -5,6 +5,7 @@
 Abc=*.abc;*.abp;
 ActionScript=*.as;
 Ada=*.adb;*.ads;
+Asciidoc=*.asciidoc;
 ASM=*.asm;
 CAML=*.ml;*.mli;
 C=*.c;*.h;

data/filetypes.asciidoc

@@ -0,0 +1,35 @@
+# For complete documentation of this file, please see Geany's main documentation
+[styling]
+# no syntax highlighting yet
+
+[settings]
+# default extension used when saving files
+extension=asciidoc
+
+# the following characters are these which a "word" can contains, see documentation
+#wordchars=_abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789
+
+# single comments, like # in this file
+comment_single=//
+# multiline comments
+#comment_open=////
+#comment_close=////
+
+# set to false if a comment character/string should start at column 0 of a line, true uses any
+# indentation of the line, e.g. setting to true causes the following on pressing CTRL+d
+	#command_example();
+# setting to false would generate this
+#	command_example();
+# This setting works only for single line comments
+#comment_use_indent=true
+
+# context action command (please see Geany's main documentation for details)
+context_action_cmd=
+
+# sort tags by appearance
+symbol_list_sort_mode=1
+
+[indentation]
+#width=4
+# 0 is spaces, 1 is tabs, 2 is tab & spaces
+#type=1

src/filetypes.c

@@ -496,6 +496,14 @@ static void init_builtin_filetypes(void)
 	ft->name = g_strdup("Forth");
 	filetype_make_title(ft, TITLE_SOURCE_FILE);
 	ft->group = GEANY_FILETYPE_GROUP_SCRIPT;
+
+#define ASCIIDOC
+	ft = filetypes[GEANY_FILETYPES_ASCIIDOC];
+	ft->lang = 43;
+	ft->name = g_strdup("Asciidoc");
+	filetype_make_title(ft, TITLE_SOURCE_FILE);
+	ft->group = GEANY_FILETYPE_GROUP_MARKUP;
+
 }
 
 

src/filetypes.h

@@ -90,6 +90,7 @@ typedef enum
 	GEANY_FILETYPES_ERLANG,
 	GEANY_FILETYPES_COBOL,
 	GEANY_FILETYPES_OBJECTIVEC,
+	GEANY_FILETYPES_ASCIIDOC,
 	/* ^ append items here */
 	GEANY_MAX_BUILT_IN_FILETYPES	/* Don't use this, use filetypes_array->len instead */
 }

src/symbols.c

@@ -807,6 +807,17 @@ static void add_top_level_items(GeanyDocument *doc)
 				NULL);
 			break;
 		}
+		case GEANY_FILETYPES_ASCIIDOC:
+		{
+			tag_list_add_groups(tag_store,
+				&(tv_iters.tag_namespace), _("Chapter"), NULL,
+				&(tv_iters.tag_member), _("Section"), NULL,
+				&(tv_iters.tag_macro), _("Level2section"), NULL,
+				&(tv_iters.tag_variable), _("Level3section"), NULL,
+				&(tv_iters.tag_struct), _("Level4section"), NULL,
+				NULL);
+			break;
+		}
 		case GEANY_FILETYPES_RUBY:
 		{
 			tag_list_add_groups(tag_store,

tagmanager/ctags/Makefile.am

@@ -13,6 +13,7 @@ noinst_LIBRARIES = libctags.a
 parsers = \
 	abc.c \
 	actionscript.c \
+	asciidoc.c \
 	asm.c \
 	basic.c \
 	c.c \

tagmanager/ctags/asciidoc.c

@@ -0,0 +1,205 @@
+/*
+*
+* 	Copyright (c) 2012, Lex Trotman
+*   Based on Rest code by Nick Treleaven, see rest.c
+*
+*   This source code is released for free distribution under the terms of the
+*   GNU General Public License.
+*
+*   This module contains functions for generating tags for asciidoc files.
+*/
+
+/*
+*   INCLUDE FILES
+*/
+#include "general.h"	/* must always come first */
+
+#include <ctype.h>
+#include <string.h>
+
+#include "parse.h"
+#include "read.h"
+#include "vstring.h"
+#include "nestlevel.h"
+
+/*
+*   DATA DEFINITIONS
+*/
+typedef enum {
+	K_CHAPTER = 0,
+	K_SECTION,
+	K_SUBSECTION,
+	K_SUBSUBSECTION,
+	K_LEVEL5SECTION,
+	SECTION_COUNT
+} asciidocKind;
+
+static kindOption AsciidocKinds[] = {
+	{ TRUE, 'n', "namespace",     "chapters"},
+	{ TRUE, 'm', "member",        "sections" },
+	{ TRUE, 'd', "macro",         "level2sections" },
+	{ TRUE, 'v', "variable",      "level3sections" },
+	{ TRUE, 's', "struct",        "level4sections" }
+};
+
+static char kindchars[SECTION_COUNT]={ '=', '-', '~', '^', '+' };
+
+static NestingLevels *nestingLevels = NULL;
+
+/*
+*   FUNCTION DEFINITIONS
+*/
+
+static NestingLevel *getNestingLevel(const int kind)
+{
+	NestingLevel *nl;
+
+	while (1)
+	{
+		nl = nestingLevelsGetCurrent(nestingLevels);
+		if (nl && nl->type >= kind)
+			nestingLevelsPop(nestingLevels);
+		else
+			break;
+	}
+	return nl;
+}
+
+static void makeAsciidocTag (const vString* const name, const int kind)
+{
+	const NestingLevel *const nl = getNestingLevel(kind);
+
+	if (vStringLength (name) > 0)
+	{
+		tagEntryInfo e;
+		initTagEntry (&e, vStringValue (name));
+
+		e.lineNumber--;	/* we want the line before the '---' underline chars */
+		e.kindName = AsciidocKinds [kind].name;
+		e.kind = AsciidocKinds [kind].letter;
+
+		if (nl && nl->type < kind)
+		{
+			e.extensionFields.scope [0] = AsciidocKinds [nl->type].name;
+			e.extensionFields.scope [1] = vStringValue (nl->name);
+		}
+		makeTagEntry (&e);
+	}
+	nestingLevelsPush(nestingLevels, name, kind);
+}
+
+
+/* checks if str is all the same character */
+static boolean issame(const char *str)
+{
+	char first = *str;
+
+	while (*str)
+	{
+		char c;
+
+		str++;
+		c = *str;
+		if (c && c != first)
+			return FALSE;
+	}
+	return TRUE;
+}
+
+
+static int get_kind(char c)
+{
+	int i;
+
+	for (i = 0; i < SECTION_COUNT; i++)
+	{
+		if (kindchars[i] == c)
+			return i;
+	}
+	return -1;
+}
+
+
+/* computes the length of an UTF-8 string
+ * if the string doesn't look like UTF-8, return -1 */
+static int utf8_strlen(const char *buf, int buf_len)
+{
+	int len = 0;
+	const char *end = buf + buf_len;
+
+	for (len = 0; buf < end; len ++)
+	{
+		/* perform quick and naive validation (no sub-byte checking) */
+		if (! (*buf & 0x80))
+			buf ++;
+		else if ((*buf & 0xe0) == 0xc0)
+			buf += 2;
+		else if ((*buf & 0xf0) == 0xe0)
+			buf += 3;
+		else if ((*buf & 0xf8) == 0xf0)
+			buf += 4;
+		else /* not a valid leading UTF-8 byte, abort */
+			return -1;
+
+		if (buf > end) /* incomplete last byte */
+			return -1;
+	}
+
+	return len;
+}
+
+
+static void findAsciidocTags (void)
+{
+	vString *name = vStringNew ();
+	const unsigned char *line;
+
+	nestingLevels = nestingLevelsNew();
+
+	while ((line = fileReadLine ()) != NULL)
+	{
+		int line_len = strlen((const char*) line);
+		int name_len_bytes = vStringLength(name);
+		int name_len = utf8_strlen(vStringValue(name), name_len_bytes);
+
+		/* if the name doesn't look like UTF-8, assume one-byte charset */
+		if (name_len < 0)
+			name_len = name_len_bytes;
+
+		/* underlines must be +-2 chars */
+		if (line_len >= name_len - 2 && line_len <= name_len + 2 && name_len > 0 &&
+			ispunct(line[0]) && issame((const char*) line))
+		{
+			char c = line[0];
+			int kind = get_kind(c);
+
+			if (kind >= 0)
+			{
+				makeAsciidocTag(name, kind);
+				continue;
+			}
+		}
+		vStringClear (name);
+		if (! isspace(*line))
+			vStringCatS(name, (const char*) line);
+		vStringTerminate(name);
+	}
+	vStringDelete (name);
+	nestingLevelsFree(nestingLevels);
+}
+
+extern parserDefinition* AsciidocParser (void)
+{
+	static const char *const patterns [] = { "*.asciidoc", NULL };
+	static const char *const extensions [] = { "asciidoc", NULL };
+	parserDefinition* const def = parserNew ("Asciidoc");
+
+	def->kinds = AsciidocKinds;
+	def->kindCount = KIND_COUNT (AsciidocKinds);
+	def->patterns = patterns;
+	def->extensions = extensions;
+	def->parser = findAsciidocTags;
+	return def;
+}
+
+/* vi:set tabstop=8 shiftwidth=4: */

tagmanager/ctags/makefile.win32

@@ -46,7 +46,7 @@ clean:
 
 $(COMPLIB): abc.o args.o c.o cobol.o fortran.o make.o conf.o pascal.o perl.o php.o diff.o vhdl.o verilog.o lua.o js.o \
 actionscript.o nsis.o objc.o \
-haskell.o haxe.o html.o python.o lregex.o rest.o sh.o ctags.o entry.o get.o keyword.o nestlevel.o \
+haskell.o haxe.o html.o python.o lregex.o asciidoc.o rest.o sh.o ctags.o entry.o get.o keyword.o nestlevel.o \
 options.o \
 parse.o basic.o read.o sort.o strlist.o latex.o markdown.o matlab.o docbook.o tcl.o ruby.o asm.o sql.o txt2tags.o css.o \
 vstring.o r.o

tagmanager/ctags/parsers.h

@@ -57,7 +57,8 @@
     VerilogParser, \
     RParser, \
     CobolParser, \
-    ObjcParser
+    ObjcParser, \
+    AsciidocParser
 /*
 langType of each parser
  0	CParser
@@ -103,6 +104,7 @@ langType of each parser
 40	RParser
 41	CobolParser
 42	ObjcParser
+43  AsciidocParser
 */
 #endif	/* _PARSERS_H */
 

wscript

@@ -64,6 +64,7 @@ ctags_sources = set([
     'tagmanager/ctags/args.c',
     'tagmanager/ctags/abc.c',
     'tagmanager/ctags/actionscript.c',
+    'tagmanager/ctags/asciidoc.c',
     'tagmanager/ctags/asm.c',
     'tagmanager/ctags/basic.c',
     'tagmanager/ctags/c.c',