rmultimarkdown 4.6.0.2 → 4.7.0.1

data/MultiMarkdown-4/parser.h

@@ -14,10 +14,10 @@
 
 #define TABSTOP 4
 
-#define MMD_VERSION "4.6"
+#define MMD_VERSION "4.7"
 
 #define MMD_COPYRIGHT \
-	"Copyright (c) 2013-2014 Fletcher T. Penney.\n\n" \
+	"Copyright (c) 2013-2015 Fletcher T. Penney.\n\n" \
 	"LyX export code (c) 2013-2014 Charles R. Cowan,\n" \
 	"licensed under both GPL and MIT licenses.\n\n" \
 	"portions based on peg-markdown - Copyright (c) 2008-2009 John MacFarlane.\n" \
@@ -71,6 +71,7 @@ typedef struct {
 	int   odf_para_type;         /* what type of paragraph do we need? */
 	bool  odf_list_needs_end_p;  /* is there a <p> that need to be closed */
 	int   random_seed_base;      /* Allow random footnotes */
+	int   toc_level;             /* Track depth for TOC */
 	int   table_row;             /* CRC - Track the current row number */
 	int   lyx_para_type;         /* CRC - the type of paragraph being processed */
 	int   lyx_level;             /* CRC - nesting level */
@@ -180,5 +181,6 @@ int tree_contains_key_count(node *list, int key);
 bool check_timeout();
 
 void debug_node(node *n);
+void debug_node_tree(node *n);
 
 #endif

data/MultiMarkdown-4/rtf.c

@@ -474,6 +474,20 @@ void print_rtf_node(GString *out, node *n, scratch_pad *scratch) {
 				free(temp);
 			}
 			break;
+		case HTMLBLOCK:
+			/* don't print HTML block */
+			/* but do print HTML comments for raw RTF */
+			if (strncmp(n->str,"<!--",4) == 0) {
+				pad(out, 2, scratch);
+				/* trim "-->" from end */
+				n->str[strlen(n->str)-3] = '\0';
+				g_string_append_printf(out, "%s", &n->str[4]);
+				scratch->padded = 0;
+			}
+			break;
+		case TOC:
+			print_rtf_node_tree(out,n->children, scratch);
+			break;
 		default:
 			fprintf(stderr, "print_rtf_node encountered unknown node key = %d\n",n->key);
 			g_string_append_printf(out, "%s",n->str);

data/MultiMarkdown-4/text.c

@@ -3,7 +3,7 @@
 	test.c -- plain text writer function as an example.
 		Recreates the input source.
 
-	(c) 2013 Fletcher T. Penney (http://fletcherpenney.net/).
+	(c) 2013-2015 Fletcher T. Penney (http://fletcherpenney.net/).
 
 	This program is free software; you can redistribute it and/or modify
 	it under the terms of the GNU General Public License or the MIT

data/MultiMarkdown-4/toc.c

@@ -0,0 +1,142 @@
+/*
+
+	toc.c -- Table of contents
+
+	(c) 2013-2015 Fletcher T. Penney (http://fletcherpenney.net/).
+
+	This program is free software; you can redistribute it and/or modify
+	it under the terms of the GNU General Public License or the MIT
+	license.  See LICENSE for details.
+	
+	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.
+
+*/
+
+#include "toc.h"
+
+
+/* print_toc_node_tree -- convert node tree to LaTeX */
+void print_toc_node_tree(GString *out, node *list, scratch_pad *scratch) {
+#ifdef DEBUG_ON
+	fprintf(stderr, "print_toc_node_tree\n");
+#endif
+	int lev;
+	while (list != NULL) {
+		if (list->key == HEADINGSECTION) {
+			lev = list->children->key;
+			
+			print_toc_section_and_children(out, list, scratch);
+			
+			while ((list->next != NULL) && (list->next->key == HEADINGSECTION)
+				&& (list->next->children->key > lev)) {
+					list = list->next;
+				}
+		} else {
+			print_toc_node(out, list, scratch);
+		}
+		list = list->next;
+	}
+}
+
+/* print_toc_section_and_children -- we want to stay inside the outline structure */
+void print_toc_section_and_children(GString *out, node *list, scratch_pad *scratch) {
+#ifdef DEBUG_ON
+	fprintf(stderr, "print_toc_section_and_children: %d\n",list->key);
+#endif
+	int lev = list->children->key;
+
+	/* print current section (parent) */
+	print_toc_node(out, list, scratch);
+
+	scratch->toc_level ++;
+	
+	/* check for child nodes */
+	while ((list->next != NULL) && (list->next->key == HEADINGSECTION) && (list->next->children->key > lev)) {
+		/* next item is also a HEADINGSECTION and is a child */
+		if (list->next->children->key - lev == 1)
+			print_toc_section_and_children(out, list->next, scratch);
+		list = list->next;
+	}
+
+	scratch->toc_level --;
+}
+
+/* print_toc_node -- convert given node to OPML and append */
+void print_toc_node(GString *out, node *n, scratch_pad *scratch) {
+	char *temp;
+	int i;
+
+#ifdef DEBUG_ON
+	fprintf(stderr, "print_toc_node: %d\n",n->key);
+#endif
+	switch (n->key) {
+		case HEADINGSECTION:
+			/* Need to handle "nesting" properly */
+			for (i = 0; i < scratch->toc_level; ++i)
+			{
+				g_string_append_printf(out, "\t");
+			}
+			g_string_append_printf(out, "* ");
+
+			/* Print header */
+			print_toc_node(out, n->children, scratch);
+
+			break;
+		case H1: case H2: case H3: case H4: case H5: case H6: 
+			if ((n->children != NULL) && (n->children->key == AUTOLABEL)) {
+				temp = label_from_string(n->children->str);
+				/* use label for header since one was specified (MMD)*/
+				g_string_append_printf(out, "[");
+				print_toc_node_tree(out, n->children, scratch);
+				g_string_append_printf(out, "][%s]\n", temp);
+			} else {
+				temp = label_from_node_tree(n->children);
+				g_string_append_printf(out, "[");
+				print_toc_node_tree(out, n->children, scratch);
+				g_string_append_printf(out, "][%s]\n", temp);
+			}
+			free(temp);
+			break;
+		case STR:
+			print_toc_string(out, n->str);
+			break;
+		case SPACE:
+			g_string_append_printf(out, "%s", n->str);
+			break;
+		case LINK:
+			print_toc_node_tree(out, n->children, scratch);
+			break;
+		case LINKREFERENCE:
+			break;
+		case AUTOLABEL:
+			break;
+		case LIST:
+			print_toc_node_tree(out, n->children, scratch);
+			break;
+		default: fprintf(stderr, "print_html_node encountered unknown node key = %d\n",n->key);
+			break;
+	}
+#ifdef DEBUG_ON
+	fprintf(stderr, "finish print_toc_node: %d\n", n->key);
+#endif
+}
+
+/* print_toc_string - print string, escaping for OPML */
+void print_toc_string(GString *out, char *str) {
+	while (*str != '\0') {
+		switch (*str) {
+			case '[':
+				g_string_append_printf(out, "\\[");
+				break;
+			case ']':
+				g_string_append_printf(out, "\\]");
+				break;
+			default:
+				g_string_append_c(out, *str);
+		}
+		str++;
+	}
+}

data/MultiMarkdown-4/toc.h

@@ -0,0 +1,15 @@
+#ifndef TOC_PARSER_H
+#define TOC_PARSER_H
+
+#include "parser.h"
+#include "writer.h"
+
+void begin_toc_output(GString *out, node* list, scratch_pad *scratch);
+void print_toc_node_tree(GString *out, node *list, scratch_pad *scratch);
+void print_toc_node(GString *out, node *n, scratch_pad *scratch);
+void print_toc_section_and_children(GString *out, node *list, scratch_pad *scratch);
+void end_toc_output(GString *out, node* list, scratch_pad *scratch);
+void print_toc_string(GString *out, char *str);
+
+
+#endif

data/MultiMarkdown-4/transclude.c

@@ -17,6 +17,9 @@
 
 #include "transclude.h"
 #include "parser.h"
+#if defined(__WIN32)
+#include <windows.h>
+#endif
 
 
 /* Combine directory and filename to create a full path */
@@ -48,19 +51,43 @@ char * path_from_dir_base(char *dir, char *base) {
 	return result;
 }
 
+/* Separate filename and directory from a full path */
+/* See http://stackoverflow.com/questions/1575278/function-to-split-a-filepath-into-path-and-file */
+void split_path_file(char** dir, char** file, char *path) {
+    char *slash = path, *next;
+#if defined(__WIN32)
+	const char sep[] = "\\";
+#else
+	const char sep[] = "/";
+#endif
+
+    while ((next = strpbrk(slash + 1, sep))) slash = next;
+    if (path != slash) slash++;
+    *dir = strndup(path, slash - path);
+    *file = strdup(slash);
+}
+
 /* Return pointer to beginning of text without metadata */
+/* NOTE: This is not a new string, and does not need to be freed separately */
 char * source_without_metadata(char * source, unsigned long extensions ) {
 	char *result;
 
 	if (has_metadata(source, extensions)) {
 		/* If we have metadata, then return just the body */
+		/* TODO: This could miss YAML Metadata that does not contain
+			blank line afterwards */
 		result = strstr(source, "\n\n");
 
 		if (result != NULL)
-			return result+2;
+			return result + 2;
 	}
 
 	/* No metadata, so return original pointer */
+
+	/* But check for UTF-8 BOM and skip if present */
+	if (strncmp(source, "\xef\xbb\xbf",3) == 0)
+		return source + 3;
+
 	return source;
 }
 
@@ -70,7 +97,7 @@ char * source_without_metadata(char * source, unsigned long extensions ) {
 	Pass the path to the current folder if available -- should be a full path. 
 
 	Keep track of what we're parsing to prevent recursion using stack. */
-void transclude_source(GString *source, char *basedir, char *stack, int output_format) {
+void transclude_source(GString *source, char *basedir, char *stack, int output_format, GString *manifest) {
 	char *base = NULL;
 	char *path = NULL;
 	char *start;
@@ -165,6 +192,18 @@ void transclude_source(GString *source, char *basedir, char *stack, int output_f
 
 			pos = stop - source->str;
 
+			/* Add to the manifest (if not already included) */
+			if (manifest != NULL) {
+				temp = strstr(manifest->str,filename->str);
+
+				if ((temp != NULL) && (temp[strlen(filename->str)] == '\n')){
+					/* Already on manifest */
+				} else {
+					g_string_append_printf(manifest,"%s\n",filename->str);
+				}
+			}
+
+
 			/* Don't reparse ourselves */
 			if (stack != NULL) {
 				temp = strstr(stack,filename->str);
@@ -177,7 +216,15 @@ void transclude_source(GString *source, char *basedir, char *stack, int output_f
 			}
 
 			/* Read file */
+#if defined(__WIN32)
+			int wchars_num = MultiByteToWideChar(CP_UTF8, 0, filename->str, -1, NULL, 0);
+			wchar_t wstr[wchars_num];
+			MultiByteToWideChar(CP_UTF8, 0, filename->str, -1, wstr, wchars_num);
+
+			if ((input = _wfopen(wstr, L"r")) != NULL ) {
+#else
 			if ((input = fopen(filename->str, "r")) != NULL ) {
+#endif
 				filebuffer = g_string_new("");
 
 				while ((curchar = fgetc(input)) != EOF)
@@ -195,8 +242,18 @@ void transclude_source(GString *source, char *basedir, char *stack, int output_f
 
 
 				/* Recursively transclude files */
-				transclude_source(filebuffer, folder->str, stackstring->str, output_format);
 
+				/* We want to reset the base directory if we enter a subdirectory */
+				char * new_dir;
+				char * file_only;
+				split_path_file(&new_dir, &file_only, filename->str);
+
+				/* transclude_source(filebuffer, folder->str, stackstring->str, output_format, manifest); */
+				transclude_source(filebuffer, new_dir, stackstring->str, output_format, manifest);
+
+				free(new_dir);
+				free(file_only);
+				
 				temp = source_without_metadata(filebuffer->str, 0x000000);
 
 				g_string_insert(source, pos, temp);
@@ -224,11 +281,27 @@ void transclude_source(GString *source, char *basedir, char *stack, int output_f
 /* Allow for a footer to specify files to be appended to the end of the text, and then transcluded.
 	Useful for appending a list of footnotes, citations, abbreviations, etc. to each separate file,
 	but not including multiple copies when processing the master file. */
-void append_mmd_footers(GString *source) {
+void append_mmd_footer(GString *source) {
 	/* Look for mmd_footer metadata */
 	if (has_metadata(source->str, 0x000000)) {
 		char *meta = extract_metadata_value(source->str, 0x000000, "mmdfooter");
 		if (meta != NULL)
-			g_string_append_printf(source, "\n\n{{%s}}\n",meta);
+			g_string_append_printf(source, "\n\n{{%s}}\n", meta);
+	}
+}
+
+void prepend_mmd_header(GString *source) {
+	/* Same thing, but to be inserted after metadata and before content */
+	if (has_metadata(source->str, 0x000000)) {
+		char *meta = extract_metadata_value(source->str, 0x000000, "mmdheader");
+		if (meta != NULL) {
+			char *content = strstr(source->str, "\n\n");
+			if (content != NULL) {
+				size_t pos = content - source->str;
+				g_string_insert_printf(source, pos, "\n\n{{%s}}", meta);
+			} else {
+				g_string_append_printf(source, "\n\n{{%s}}\n", meta);
+			}
+		}
 	}
 }

data/MultiMarkdown-4/transclude.h

@@ -23,5 +23,6 @@
 #include "GLibFacade.h"
 
 char *	source_without_metadata(char * source, unsigned long extensions);
-void	transclude_source(GString *source, char *basedir, char *stack, int format);
-void append_mmd_footers(GString *source);
+void	transclude_source(GString *source, char *basedir, char *stack, int format, GString *manifest);
+void	append_mmd_footer(GString *source);
+void	prepend_mmd_header(GString *source);

data/MultiMarkdown-4/writer.c

@@ -3,7 +3,7 @@
 	writer.c -- General routines for converting parse structure to various 
 		output formats.
 
-	(c) 2013 Fletcher T. Penney (http://fletcherpenney.net/).
+	(c) 2013-2015 Fletcher T. Penney (http://fletcherpenney.net/).
 
 	Derived from peg-multimarkdown, which was forked from peg-markdown,
 	which is (c) 2008 John MacFarlane (jgm at berkeley dot edu), and 
@@ -41,13 +41,13 @@ char * export_node_tree(node *list, int format, unsigned long extensions) {
 		(format != CRITIC_ACCEPT_FORMAT) &&
 		(format != CRITIC_REJECT_FORMAT) &&
 		(format != CRITIC_HTML_HIGHLIGHT_FORMAT)) {
-			/* Parse for link, images, etc reference definitions */
-			extract_references(list, scratch);
-
 			/* Find defined abbreviations */
 			extract_abbreviations(list, scratch);
 			/* Apply those abbreviations to source text */
 			find_abbreviations(list, scratch);
+
+			/* Parse for link, images, etc reference definitions */
+			extract_references(list, scratch);
 		}
 	
 	/* Change our desired format based on metadata */
@@ -138,6 +138,10 @@ char * export_node_tree(node *list, int format, unsigned long extensions) {
 		case CRITIC_HTML_HIGHLIGHT_FORMAT:
 			print_critic_html_highlight_node_tree(out, list, scratch);
 			break;
+		case TOC_FORMAT:
+			scratch->toc_level = 0;
+			print_toc_node_tree(out,list,scratch);
+			break;
 		default:
 			fprintf(stderr, "Unknown export format = %d\n",format);
 			exit(EXIT_FAILURE);
@@ -225,6 +229,8 @@ void extract_abbreviations(node *list, scratch_pad *scratch) {
 			case HEADINGSECTION:
 			case RAW:
 			case LIST:
+			case BLOCKQUOTEMARKER:
+			case BLOCKQUOTE:
 				extract_abbreviations(list->children, scratch);
 				break;
 			default:
@@ -293,11 +299,19 @@ void find_abbreviations(node *list, scratch_pad *scratch) {
 				}
 				break;
 			case LIST:
+			case ORDEREDLIST:
+			case BULLETLIST:
+			case LISTITEM:
 			case HEADINGSECTION:
 			case PARA:
+			case PLAIN:
 			case LINK:
 			case LINKREFERENCE:
 			case NOTEREFERENCE:
+			case NOTESOURCE:
+			case GLOSSARYSOURCE:
+			case BLOCKQUOTEMARKER:
+			case BLOCKQUOTE:
 				/* Check children of these elements */
 				find_abbreviations(list->children, scratch);
 				break;
@@ -714,4 +728,4 @@ link_data * load_link_data(node *n, scratch_pad *scratch) {
 	}
 
 	return r;
-}
+}

data/MultiMarkdown-4/writer.h

@@ -11,6 +11,7 @@
 #include "odf.h"
 #include "rtf.h"
 #include "critic.h"
+#include "toc.h"
 
 char * export_node_tree(node *list, int format, unsigned long extensions);