Markdown parser

Tmain/list-fields-with-prefix.d/stdout-expected.txt

@@ -11,6 +11,7 @@ x       UCTAGSxpath         no      NONE             s--    no    xpath for the
 -       UCTAGStemplate      no      C++              s--    no    template parameters
 -       UCTAGSproperties    no      CUDA             s--    no    properties (static, inline, mutable,...)
 -       UCTAGSassignment    yes     LdScript         s--    no    how a value is assigned to the symbol
+-       UCTAGSsectionMarker no      Markdown         s--    no    character used for declaring section(#, ##, =, or -)
 -       UCTAGShome          yes     Passwd           s--    no    home directory
 -       UCTAGSshell         yes     Passwd           s--    no    login shell
 -       UCTAGSdecorators    no      Python           s--    no    decorators on functions and classes

Tmain/list-fields.d/stdout-expected.txt

@@ -29,6 +29,7 @@ z	kind	no	NONE	s--	no	Include the "kind:" key in kind field (use k or K) in tags
 -	template	no	C++	s--	no	template parameters
 -	properties	no	CUDA	s--	no	properties (static, inline, mutable,...)
 -	assignment	yes	LdScript	s--	no	how a value is assigned to the symbol
+-	sectionMarker	no	Markdown	s--	no	character used for declaring section(#, ##, =, or -)
 -	home	yes	Passwd	s--	no	home directory
 -	shell	yes	Passwd	s--	no	login shell
 -	decorators	no	Python	s--	no	decorators on functions and classes

Units/simple-markdown.d/args.ctags

@@ -0,0 +1,2 @@
+--sort=no
+--fields-Markdown=+{sectionMarker}

Units/simple-markdown.d/expected.tags

@@ -0,0 +1,27 @@
+a	input.md	/^# a$/;"	c	sectionMarker:#
+b	input.md	/^## b$/;"	s	sectionMarker:#
+c	input.md	/^### c$/;"	S	sectionMarker:#
+d	input.md	/^#### d$/;"	t	sectionMarker:#
+e	input.md	/^##### e$/;"	T	sectionMarker:#
+f	input.md	/^###### f$/;"	u	sectionMarker:#
+g	input.md	/^# g #$/;"	c	sectionMarker:##
+h	input.md	/^# h ##$/;"	c	sectionMarker:##
+i	input.md	/^## i #$/;"	s	sectionMarker:##
+j	input.md	/^## j ##$/;"	s	sectionMarker:##
+k	input.md	/^## k ###$/;"	s	sectionMarker:##
+l	input.md	/^### l #$/;"	S	sectionMarker:##
+m	input.md	/^### m ##$/;"	S	sectionMarker:##
+n	input.md	/^### n ###$/;"	S	sectionMarker:##
+o	input.md	/^### o ###$/;"	S	sectionMarker:##
+p	input.md	/^#### p #$/;"	t	sectionMarker:##
+q	input.md	/^#### q #####$/;"	t	sectionMarker:##
+r	input.md	/^##### r #$/;"	T	sectionMarker:##
+s	input.md	/^##### s ######$/;"	T	sectionMarker:##
+t	input.md	/^###### t #$/;"	u	sectionMarker:##
+u	input.md	/^###### u #######$/;"	u	sectionMarker:##
+A	input.md	/^A$/;"	c	sectionMarker:=
+B	input.md	/^B$/;"	c	sectionMarker:=
+C	input.md	/^C$/;"	c	sectionMarker:=
+D	input.md	/^D$/;"	s	sectionMarker:-
+E	input.md	/^E$/;"	s	sectionMarker:-
+F	input.md	/^F$/;"	s	sectionMarker:-

Units/simple-markdown.d/input.md

@@ -0,0 +1,51 @@
+# a
+
+## b
+
+### c
+
+#### d
+
+##### e
+
+###### f
+
+# g #
+# h ##
+
+## i #
+## j ##
+## k ###
+
+### l #
+### m ##
+### n ###
+### o ###
+
+#### p #
+#### q #####
+
+##### r #
+##### s ######
+
+###### t #
+###### u #######
+
+A
+=
+
+B
+==
+
+C
+===
+
+D
+-
+
+E
+--
+
+F
+---
+

Units/simple-passwd.d/args.ctags

@@ -0,0 +1 @@
+--map-passwd=+.passwd

Units/simple-passwd.d/expected.tags

@@ -0,0 +1,2 @@
+bin	input.passwd	/^bin:x:1:1:bin:\/bin:\/sbin\/nologin$/;"	u	home:/bin	shell:/sbin/nologin
+root	input.passwd	/^root:x:0:0:root:\/root:\/bin\/bash$/;"	u	home:/root	shell:/bin/bash

Units/simple-passwd.d/input.passwd

@@ -0,0 +1,2 @@
+root:x:0:0:root:/root:/bin/bash
+bin:x:1:1:bin:/bin:/sbin/nologin

docs/news.rst

@@ -59,6 +59,7 @@ The following parsers have been added:
 * JSON
 * GNU linker script(LdScript)
 * Man page *optlib*
+* Markdown *optlib*
 * Maven2 *libxml*
 * M4
 * ObjectiveC

main/parsers.h

@@ -81,6 +81,7 @@
 	M4Parser, \
 	ManParser, \
 	MakefileParser, \
+	MarkdownParser, \
 	MatLabParser, \
 	MyrddinParser, \
 	ObjcParser, \

makefiles/translator_input.mak

@@ -5,6 +5,7 @@ TRANSLATOR_INPUT = \
 	optlib/elm.ctags		\
 	optlib/gdbinit.ctags			\
 	optlib/man.ctags			\
+	optlib/markdown.ctags			\
 	optlib/passwd.ctags			\
 	optlib/pod.ctags			\
 	optlib/qemuhx.ctags			\

optlib/markdown.c

@@ -0,0 +1,138 @@
+/*
+ * Generated by ./misc/optlib2c from optlib/markdown.ctags, Don't edit this manually.
+ */
+#include "general.h"
+#include "parse.h"
+#include "routines.h"
+
+
+static void initializeMarkdownParser (const langType language CTAGS_ATTR_UNUSED)
+{
+
+	addLanguageRegexTable (language, "main");
+	addLanguageRegexTable (language, "sharp");
+
+	addLanguageTagMultiTableRegex (language, "main",
+	                               "^#",
+	                               "", "", "{tjump=sharp}{_advanceTo=0start}", NULL);
+	addLanguageTagMultiTableRegex (language, "main",
+	                               "^([^\n]+)[\n]=+[\n]",
+	                               "\\1", "c", "{_field=sectionMarker:=}", NULL);
+	addLanguageTagMultiTableRegex (language, "main",
+	                               "^([^\n]+)[\n]-+[\n]",
+	                               "\\1", "s", "{_field=sectionMarker:-}", NULL);
+	addLanguageTagMultiTableRegex (language, "main",
+	                               "^[^\n]+[\n]",
+	                               "", "", "", NULL);
+	addLanguageTagMultiTableRegex (language, "main",
+	                               "^[\n]+",
+	                               "", "", "", NULL);
+	addLanguageTagMultiTableRegex (language, "main",
+	                               "^[^\n]+",
+	                               "", "", "", NULL);
+	addLanguageTagMultiTableRegex (language, "sharp",
+	                               "^#[ \t]+([^\n]+)([ \t]+#+)[\n]",
+	                               "\\1", "c", "{_field=sectionMarker:##}{tjump=main}", NULL);
+	addLanguageTagMultiTableRegex (language, "sharp",
+	                               "^##[ \t]+([^\n]+)([ \t]+#+)[\n]",
+	                               "\\1", "s", "{_field=sectionMarker:##}{tjump=main}", NULL);
+	addLanguageTagMultiTableRegex (language, "sharp",
+	                               "^###[ \t]+([^\n]+)([ \t]+#+)[\n]",
+	                               "\\1", "S", "{_field=sectionMarker:##}{tjump=main}", NULL);
+	addLanguageTagMultiTableRegex (language, "sharp",
+	                               "^####[ \t]+([^\n]+)([ \t]+#+)[\n]",
+	                               "\\1", "t", "{_field=sectionMarker:##}{tjump=main}", NULL);
+	addLanguageTagMultiTableRegex (language, "sharp",
+	                               "^#####[ \t]+([^\n]+)([ \t]+#+)[\n]",
+	                               "\\1", "T", "{_field=sectionMarker:##}{tjump=main}", NULL);
+	addLanguageTagMultiTableRegex (language, "sharp",
+	                               "^######[ \t]+([^\n]+)([ \t]+#+)[\n]",
+	                               "\\1", "u", "{_field=sectionMarker:##}{tjump=main}", NULL);
+	addLanguageTagMultiTableRegex (language, "sharp",
+	                               "^#[ \t]+([^\n]+)[\n]",
+	                               "\\1", "c", "{_field=sectionMarker:#}{tjump=main}", NULL);
+	addLanguageTagMultiTableRegex (language, "sharp",
+	                               "^##[ \t]+([^\n]+)[\n]",
+	                               "\\1", "s", "{_field=sectionMarker:#}{tjump=main}", NULL);
+	addLanguageTagMultiTableRegex (language, "sharp",
+	                               "^###[ \t]+([^\n]+)[\n]",
+	                               "\\1", "S", "{_field=sectionMarker:#}{tjump=main}", NULL);
+	addLanguageTagMultiTableRegex (language, "sharp",
+	                               "^####[ \t]+([^\n]+)[\n]",
+	                               "\\1", "t", "{_field=sectionMarker:#}{tjump=main}", NULL);
+	addLanguageTagMultiTableRegex (language, "sharp",
+	                               "^#####[ \t]+([^\n]+)[\n]",
+	                               "\\1", "T", "{_field=sectionMarker:#}{tjump=main}", NULL);
+	addLanguageTagMultiTableRegex (language, "sharp",
+	                               "^######[ \t]+([^\n]+)[\n]",
+	                               "\\1", "u", "{_field=sectionMarker:#}{tjump=main}", NULL);
+	addLanguageTagMultiTableRegex (language, "sharp",
+	                               "^[^\n]+[\n]",
+	                               "", "", "{tjump=main}", NULL);
+	addLanguageTagMultiTableRegex (language, "sharp",
+	                               "^[\n]+",
+	                               "", "", "{tjump=main}", NULL);
+	addLanguageTagMultiTableRegex (language, "sharp",
+	                               "^[^\n]+",
+	                               "", "", "{tjump=main}", NULL);
+}
+
+extern parserDefinition* MarkdownParser (void)
+{
+	static const char *const extensions [] = {
+		"md",
+		"markdown",
+		NULL
+	};
+
+	static const char *const aliases [] = {
+		NULL
+	};
+
+	static const char *const patterns [] = {
+		NULL
+	};
+
+	static kindDefinition MarkdownKindTable [] = {
+		{
+		  true, 'c', "chapter", "chapsters",
+		},
+		{
+		  true, 's', "section", "sections",
+		},
+		{
+		  true, 'S', "subsection", "subsections",
+		},
+		{
+		  true, 't', "subsubsection", "subsubsections",
+		},
+		{
+		  true, 'T', "l4subsection", "level 4 subsections",
+		},
+		{
+		  true, 'u', "l5subsection", "level 5 subsections",
+		},
+	};
+	static fieldDefinition MarkdownFieldTable [] = {
+		{
+		  .enabled     = false,
+		  .name        = "sectionMarker",
+		  .description = "character used for declaring section(#, ##, =, or -)",
+		},
+	};
+
+	parserDefinition* const def = parserNew ("Markdown");
+
+	def->enabled       = true;
+	def->extensions    = extensions;
+	def->patterns      = patterns;
+	def->aliases       = aliases;
+	def->method        = METHOD_NOT_CRAFTED|METHOD_REGEX;
+	def->kindTable = MarkdownKindTable;
+	def->kindCount = ARRAY_SIZE(MarkdownKindTable);
+	def->fieldTable = MarkdownFieldTable;
+	def->fieldCount = ARRAY_SIZE(MarkdownFieldTable);
+	def->initialize    = initializeMarkdownParser;
+
+	return def;
+}

optlib/markdown.ctags

@@ -0,0 +1,68 @@
+#
+#
+#  Copyright (c) 2018, Red Hat, Inc.
+#  Copyright (c) 2018, Masatake YAMATO
+#
+#  Author: Masatake YAMATO <[email protected]>
+#
+# This program is free software; you can redistribute it and/or
+# modify it under the terms of the GNU General Public License
+# as published by the Free Software Foundation; either version 2
+# of the License, or (at your option) any later version.
+#
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
+# along with this program; if not, write to the Free Software
+# Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301,
+# USA.
+#
+#
+
+#
+# TODO: Tracking the scope
+#
+
+--langdef=Markdown
+--map-Markdown=+.md
+--map-Markdown=+.markdown
+
+--kinddef-Markdown=c,chapter,chapsters
+--kinddef-Markdown=s,section,sections
+--kinddef-Markdown=S,subsection,subsections
+--kinddef-Markdown=t,subsubsection,subsubsections
+--kinddef-Markdown=T,l4subsection,level 4 subsections
+--kinddef-Markdown=u,l5subsection,level 5 subsections
+
+--_fielddef-Markdown=sectionMarker,character used for declaring section(#, ##, =, or -)
+
+--_tabledef-Markdown=main
+--_tabledef-Markdown=sharp
+
+
+--_mtable-regex-Markdown=main/^#///{tjump=sharp}{_advanceTo=0start}
+--_mtable-regex-Markdown=main/^([^\n]+)[\n]=+[\n]/\1/c/{_field=sectionMarker:=}
+--_mtable-regex-Markdown=main/^([^\n]+)[\n]-+[\n]/\1/s/{_field=sectionMarker:-}
+--_mtable-regex-Markdown=main/^[^\n]+[\n]//
+--_mtable-regex-Markdown=main/[\n]+//
+--_mtable-regex-Markdown=main/^[^\n]+//
+
+
+--_mtable-regex-Markdown=sharp/^#[ \t]+([^\n]+)([ \t]+#+)[\n]/\1/c/{_field=sectionMarker:##}{tjump=main}
+--_mtable-regex-Markdown=sharp/^##[ \t]+([^\n]+)([ \t]+#+)[\n]/\1/s/{_field=sectionMarker:##}{tjump=main}
+--_mtable-regex-Markdown=sharp/^###[ \t]+([^\n]+)([ \t]+#+)[\n]/\1/S/{_field=sectionMarker:##}{tjump=main}
+--_mtable-regex-Markdown=sharp/^####[ \t]+([^\n]+)([ \t]+#+)[\n]/\1/t/{_field=sectionMarker:##}{tjump=main}
+--_mtable-regex-Markdown=sharp/^#####[ \t]+([^\n]+)([ \t]+#+)[\n]/\1/T/{_field=sectionMarker:##}{tjump=main}
+--_mtable-regex-Markdown=sharp/^######[ \t]+([^\n]+)([ \t]+#+)[\n]/\1/u/{_field=sectionMarker:##}{tjump=main}
+--_mtable-regex-Markdown=sharp/^#[ \t]+([^\n]+)[\n]/\1/c/{_field=sectionMarker:#}{tjump=main}
+--_mtable-regex-Markdown=sharp/^##[ \t]+([^\n]+)[\n]/\1/s/{_field=sectionMarker:#}{tjump=main}
+--_mtable-regex-Markdown=sharp/^###[ \t]+([^\n]+)[\n]/\1/S/{_field=sectionMarker:#}{tjump=main}
+--_mtable-regex-Markdown=sharp/^####[ \t]+([^\n]+)[\n]/\1/t/{_field=sectionMarker:#}{tjump=main}
+--_mtable-regex-Markdown=sharp/^#####[ \t]+([^\n]+)[\n]/\1/T/{_field=sectionMarker:#}{tjump=main}
+--_mtable-regex-Markdown=sharp/^######[ \t]+([^\n]+)[\n]/\1/u/{_field=sectionMarker:#}{tjump=main}
+--_mtable-regex-Markdown=sharp/^[^\n]+[\n]//{tjump=main}
+--_mtable-regex-Markdown=sharp/[\n]+//{tjump=main}
+--_mtable-regex-Markdown=sharp/^[^\n]+//{tjump=main}

win32/ctags_vs2013.vcxproj

@@ -143,6 +143,7 @@
     <ClCompile Include="..\optlib\elm.c" />
     <ClCompile Include="..\optlib\gdbinit.c" />
     <ClCompile Include="..\optlib\man.c" />
+    <ClCompile Include="..\optlib\markdown.c" />
     <ClCompile Include="..\optlib\passwd.c" />
     <ClCompile Include="..\optlib\pod.c" />
     <ClCompile Include="..\optlib\puppetManifest.c" />

win32/ctags_vs2013.vcxproj.filters

@@ -183,6 +183,9 @@
     <ClCompile Include="..\optlib\man.c">
       <Filter>Source Files\optlib</Filter>
     </ClCompile>
+    <ClCompile Include="..\optlib\markdown.c">
+      <Filter>Source Files\optlib</Filter>
+    </ClCompile>
     <ClCompile Include="..\optlib\passwd.c">
       <Filter>Source Files\optlib</Filter>
     </ClCompile>