Pointer qualifier fix

TODO: No indentation on first line

COPYING

@@ -0,0 +1,22 @@
+COPYRIGHT (C) 2015-2017 by David Baer <david@amyanddavid.net>
+
+Redistribution and use in source and binary forms, with or without
+modification, are permitted provided that the following conditions
+are met:
+
+1. Redistributions of source code must retain the above copyright
+   notice, this list of conditions and the following disclaimer.
+2. Redistributions in binary form must reproduce the above copyright
+   notice, this list of conditions and the following disclaimer in the
+   documentation and/or other materials provided with the distribution.
+
+THIS SOFTWARE IS PROVIDED BY THE AUTHOR ``AS IS'' AND ANY EXPRESS OR
+IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES
+OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED.
+IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR ANY DIRECT, INDIRECT,
+INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT
+NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+(INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF
+THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.

INSTALL

@@ -0,0 +1 @@
+/usr/local/share/automake-1.15/INSTALL

Makefile.am

@@ -1,2 +1,3 @@
 SUBDIRS = src data
 dist_doc_DATA = README.md
+dist_man1_MANS = sermon.1

README.md

@@ -1,4 +1,4 @@
-sermon 1.0
+sermon 1.4
 ==========
 
 This utility converts text markup into various presentable forms.

configure.ac

@@ -2,13 +2,13 @@
 # Process this file with autoconf to produce a configure script.
 
 AC_PREREQ([2.69])
-AC_INIT([sermon], [1.1], [david.a.baer@gmail.com])
+AC_INIT([sermon], [1.5], [david.a.baer@gmail.com])
 AM_INIT_AUTOMAKE([-Wall -Werror foreign])
 AC_CONFIG_SRCDIR([config.h.in])
 AC_CONFIG_HEADERS([config.h])
 
 # Checks for programs.
-AC_PROG_CC
+AC_PROG_CC_C99
 AC_PROG_LEX
 AC_PROG_YACC
 
@@ -24,16 +24,20 @@ AC_CHECK_HEADERS([inttypes.h libintl.h limits.h malloc.h stddef.h stdint.h stdli
 AC_C_INLINE
 AC_TYPE_INT16_T
 AC_TYPE_INT32_T
+AC_TYPE_INT64_T
 AC_TYPE_INT8_T
+AC_TYPE_PID_T
 AC_TYPE_SIZE_T
 AC_TYPE_UINT16_T
 AC_TYPE_UINT32_T
+AC_TYPE_UINT64_T
 AC_TYPE_UINT8_T
 
 # Checks for library functions.
+AC_FUNC_FORK
 AC_FUNC_MALLOC
 AC_FUNC_REALLOC
-AC_CHECK_FUNCS([memset pledge realpath strdup strndup])
+AC_CHECK_FUNCS([localtime_r pledge memset realpath strcasecmp strdup strndup strrchr])
 
 AC_CONFIG_FILES([Makefile
                  data/Makefile

data/ms_odt.xsl

@@ -78,7 +78,7 @@
  </xsl:template>
 
  <xsl:template match="ser:p" mode="quote">
-     <text:p text:style-name="Quotations"><text:span text:style-name="T2"><xsl:apply-templates select="*|text()"/></text:span></text:p>
+     <text:p text:style-name="Quotations"><xsl:apply-templates select="*|text()"/></text:p>
  </xsl:template>
 
  <xsl:template match="ser:quote" mode="body">

src/format.c

@@ -27,6 +27,7 @@
  * 
  */
 
+#include <ctype.h>
 #include <string.h>
 #include "queue.h"
 #include "stack.h"
@@ -45,6 +46,7 @@ typedef enum {
     TOK_STAR,
     TOK_REF,
     TOK_URL,
+    TOK_BREAK,
     /*
     TOK_DASH,
     TOK_OPEN_DOUBLE_QUOTE,
@@ -69,35 +71,35 @@ freeTokenizer(utf8iterator* iter) {
     utf8FreeIterator(iter);
 }
 
-inline int
+int
 greekChar(uint32_t ch) {
     return (((0x370 <= ch) && (ch <= 0x3ff)) ||
             ((0x1f00 <= ch) && (ch <= 0x1fff)));
 }
 
-inline int
+int
 extendedPunctuation(uint32_t ch) {
     return ((0x2000 <= ch) && (ch <= 0x206f));
 }
 
-inline int
+int
 latinChar(uint32_t ch) {
     return (ch <= 0xff) || extendedPunctuation(ch);
 }
 
-inline int
+int
 httpAt(Tokenizer tokenizer) {
     return ((tolower(tokenizer->txt[tokenizer->byteIndex]) == 'h') &&
             (tolower(tokenizer->txt[tokenizer->byteIndex + 1]) == 't') &&
             (tolower(tokenizer->txt[tokenizer->byteIndex + 2]) == 't') &&
             (tolower(tokenizer->txt[tokenizer->byteIndex + 3]) == 'p') &&
-            ((tokenizer->txt[tokenizer->byteIndex + 4] == ':') &&
+            (((tokenizer->txt[tokenizer->byteIndex + 4] == ':') &&
               (tokenizer->txt[tokenizer->byteIndex + 5] == '/') &&
               (tokenizer->txt[tokenizer->byteIndex + 6] == '/')) ||
              ((tolower(tokenizer->txt[tokenizer->byteIndex + 4]) == 's') &&
               (tokenizer->txt[tokenizer->byteIndex + 5] == ':') &&
               (tokenizer->txt[tokenizer->byteIndex + 6] == '/') &&
-             (tokenizer->txt[tokenizer->byteIndex + 7] == '/')));
+              (tokenizer->txt[tokenizer->byteIndex + 7] == '/'))));
 }
 
 static Token
@@ -115,6 +117,11 @@ nextToken(Tokenizer tokenizer) {
         result.toktype = TOK_STAR;
         result.toktext = NULL;
         return result;
+    } else if (ch == '\n') {
+        utf8Advance(tokenizer);
+        result.toktype = TOK_BREAK;
+        result.toktext = NULL;
+        return result;
     } else if (greekChar(ch)) {
         while ((ch != 0) &&
                (greekChar(ch) || (ch == ' ') || (ch == ',') || (ch == '.'))) {
@@ -158,7 +165,7 @@ nextToken(Tokenizer tokenizer) {
         result.toktext = strndup(tokenizer->txt + startIndex, endIndex - startIndex);
         return result;
     } else if (latinChar(ch)) {
-        while ((ch != 0) && latinChar(ch) && (ch != '*')) {
+        while ((ch != 0) && latinChar(ch) && (ch != '*') && (ch != '\n')) {
             utf8Advance(tokenizer);
             ch = utf8CharAt(tokenizer);
             if (ch == '^') {
@@ -206,6 +213,10 @@ int formatText(const char* txt, FormatElement** dst, CitationRecordQueue* citati
                 REINIT_QUEUE(formatElementQ);
                 em = 1;
             }
+        } else if (tok.toktype == TOK_BREAK) {
+            FormatElement elt = { .elementType = FORMAT_BR, .elementContentLength = 0,
+                                  .elementContent = { .textContent = NULL } };
+            APPEND_QUEUE(FormatElementQueue, formatElementQ, elt);
         } else {
             FormatElementType t;
             FormatElement elt = { .elementContent = { .textContent = tok.toktext } } ;

src/format.h

@@ -34,6 +34,7 @@
 typedef enum {
     FORMAT_TEXT,
     FORMAT_EM,
+    FORMAT_BR,
     FORMAT_STRONG,
     FORMAT_CITATION,
     FORMAT_GREEK,

src/odt.c

@@ -31,6 +31,7 @@
 #include <stdlib.h>
 #include <string.h>
 #include <unistd.h>
+#include <sys/wait.h>
 #include "odt.h"
 #include "options.h"
 
@@ -50,7 +51,7 @@ extractTemplateDocument(const char* const templateFilename, const char* const te
     pid_t child_pid;
     if ((child_pid = fork()) == 0) {
         /* you are the child */
-        char* const args[] = { "unzip", "-d", tempDir, templateFilename, NULL };
+        char* const args[] = { "unzip", "-d", (char* const)tempDir, (char* const)templateFilename, NULL };
         freopen("/dev/null", "w", stdout);
         execvp("unzip", args);
         perror("execvp");
@@ -72,9 +73,40 @@ createOutputDocument(const char* const outputFilename, const char* const tempDir
     pid_t child_pid;
     if ((child_pid = fork()) == 0) {
         /* you are the child */
+
+	/* In some implementations, realpath will give an error
+	 * if the file does not exist, so we need to run it on
+	 * the output directory, not the as-yet nonexistent
+	 * output filename. That's what all this (below) is for. */
+	char outputDir[FILENAME_MAX];
+	char outputBase[FILENAME_MAX];
         char outputRealPath[FILENAME_MAX];
-        char* const args[] = { "zip", "-r", outputRealPath, ".", NULL };
-        realpath(outputFilename, outputRealPath);
+	strncpy(outputDir, outputFilename, FILENAME_MAX);
+	char *ptr = strrchr(outputDir, '/');
+	if (ptr) {
+	    strncpy(outputBase, ptr + 1, FILENAME_MAX);
+	    *(ptr + 1) = '\0';
+	} else {
+	    strncpy(outputDir, ".", FILENAME_MAX);
+	    strncpy(outputBase, outputFilename, FILENAME_MAX);
+	}
+
+        if (realpath(outputDir, outputRealPath) == NULL) {
+            /* hopefully this doesn't run, but it will give good info
+	     * if it does */
+	    perror("realpath");
+	    fprintf(stderr, "outputFilename was \"%s\"\n", outputFilename);
+	    char curdir[FILENAME_MAX];
+	    getcwd(curdir, FILENAME_MAX);
+	    fprintf(stderr, "curdir was \"%s\"\n", curdir);
+	    exit(1);
+	}
+
+	/* Then we append the output filename. */
+	strncat(outputRealPath, "/", FILENAME_MAX);
+	strncat(outputRealPath, outputBase, FILENAME_MAX);
+
+        char* const args[] = { "zip", "-r", outputRealPath, "mimetype", ".", NULL };
         chdir(tempDir);
         freopen("/dev/null", "w", stdout);
         execvp("zip", args);
@@ -97,7 +129,7 @@ removeDirectory(const char* const tempDir) {
     pid_t child_pid;
     if ((child_pid = fork()) == 0) {
         /* you are the child */
-        char* const args[] = { "rm", "-rf", tempDir, NULL };
+        char* const args[] = { "rm", "-rf", (char* const)tempDir, NULL };
         freopen("/dev/null", "w", stdout);
         execvp("rm", args);
         perror("execvp");

src/queue.h

@@ -69,7 +69,7 @@ typedef struct { \
 } N
 
 #define NEW_QUEUE(T, N) \
-    T N = (T) { .length = 0, .head = NULL, .tail = NULL }
+    T N = { .length = 0, .head = NULL, .tail = NULL }
 
 /* WARNING: this is probably not what you want -- see DESTROY_QUEUE below */
 #define REINIT_QUEUE(N) { \

src/sermon.h

@@ -38,7 +38,8 @@ typedef struct {
 
 typedef enum {
     PARA_DEFAULT,
-    PARA_BLOCKQUOTE
+    PARA_BLOCKQUOTE,
+    PARA_BLOCKPRESERVE
 } SermonParagraphType;
 
 typedef struct {

src/sermon_lexer.l

@@ -9,6 +9,7 @@
 #define LEXPRINT(x...)
 #endif
 %}
+%option noyywrap
 %s HEADER HEADERVAL REFERENCEINTRO REFERENCENAME REFERENCE BLOCK
 WHITESPACE                   [ \t]
 ID                           [A-Za-z_][A-Za-z_0-9]*
@@ -26,10 +27,19 @@ ID                           [A-Za-z_][A-Za-z_0-9]*
 <REFERENCENAME>:             { BEGIN(REFERENCE); yylloc.first_column = ++yylloc.last_column; return ':'; }
 <REFERENCE>[^}]*             { yylloc.first_column = yylloc.last_column + 1; yylloc.last_column = yylloc.first_column + strlen(yytext) + 1; yylval.sval = strdup(yytext); return REFTEXT; }
 <REFERENCE>[}]               { BEGIN(INITIAL); yylloc.first_column = ++yylloc.last_column; return '}'; }
-^[^[{>\n].*                   { yylloc.first_column = ++yylloc.last_column; yylval.sval = strdup(yytext); LEXPRINT("LINE: %s\n", yytext); return LINE; }
-^>{WHITESPACE}*\n             { yylloc.first_column = yylloc.last_column = 0; yylloc.first_line++; yylloc.last_line++; return '\n'; }
-^>{WHITESPACE}*               { BEGIN(BLOCK); yylloc.first_column = yylloc.last_column = 1; return '>'; }
-<BLOCK>..*                   { BEGIN(INITIAL); yylloc.first_column = yylloc.last_column + 1; yylloc.last_column = yylloc.first_column + strlen(yytext) - 1; yylval.sval = strdup(yytext); return LINE; }
+^[^[{>|\n].*                 { yylloc.first_column = ++yylloc.last_column; yylval.sval = strdup(yytext); LEXPRINT("LINE: %s\n", yytext); return LINE; }
+^[>|]{WHITESPACE}*\n         { yylloc.first_column = yylloc.last_column = 0; yylloc.first_line++; yylloc.last_line++; return '\n'; }
+^[>|]{WHITESPACE}*           {
+                                 BEGIN(BLOCK);
+                                 yylloc.first_column = yylloc.last_column = 1;
+                                 return yytext[0];
+                             }
+<BLOCK>..*                   {
+                                 BEGIN(INITIAL);
+                                 yylloc.first_column = yylloc.last_column + 1;
+                                 yylloc.last_column = yylloc.first_column + strlen(yytext) - 1;
+                                 yylval.sval = strdup(yytext); return LINE;
+                             }
 <INITIAL>\n                  { yylloc.first_column = yylloc.last_column = 0; yylloc.first_line++; yylloc.last_line++; return '\n'; }
 <<EOF>>                      { return 0; }
 %%

src/sermon_parser.y

@@ -37,7 +37,13 @@ char* lineQueueToString(LineQueue* lq) {
     FOREACH_QUEUE(LineQueue, *lq, ptr) {
         strncat(dest + idx, ptr->data, paraLength - idx);
         idx += strlen(ptr->data);
-        if (ptr->next != NULL) dest[idx++] = ' ';
+        if (ptr->next != NULL) {
+            if (dest[idx-1] != '\n')
+                dest[idx++] = ' ';
+        } else {
+            if (dest[idx-1] == '\n')
+               idx--;
+        }
         free(ptr->data);
     }
     FOREACH_QUEUE_END
@@ -45,6 +51,14 @@ char* lineQueueToString(LineQueue* lq) {
     return dest;
 }
 
+char *lineWithBreak(const char *txt) {
+    size_t l = strlen(txt);
+    char* s = (char*)malloc(l+2);
+    strncpy(s, txt, l + 2);
+    s[l] = '\n';
+    return s;
+}
+
 void yyerror(Sermon*, const char*);
 
 %}
@@ -126,7 +140,7 @@ block:
          PARSEPRINT("Parsed paragraph:\n%s\n\n", p.paraText);
          free(paraText);
      }
-   | blockquote {
+   | blockquote_or_preserve {
          SermonParagraph p = { .paraType = PARA_BLOCKQUOTE };
          char* paraText = lineQueueToString(&lineQ);
          FormatElement* paraContent = NULL;
@@ -142,10 +156,17 @@ para:
     para LINE '\n' { APPEND_QUEUE(LineQueue, lineQ, $2); }
   | LINE '\n'      { DESTROY_QUEUE(LineQueue, lineQ); APPEND_QUEUE(LineQueue, lineQ, $1); }
   ;
+blockquote_or_preserve:
+          blockquote
+        | blockpreserve
+        ;
 blockquote:
           blockquote '>' LINE '\n' { APPEND_QUEUE(LineQueue, lineQ, $3); }
         | '>' LINE '\n' { DESTROY_QUEUE(LineQueue, lineQ); APPEND_QUEUE(LineQueue, lineQ, $2); }
         ;
+blockpreserve:
+          blockpreserve '|' LINE '\n' { char* s = lineWithBreak($3); APPEND_QUEUE(LineQueue, lineQ, s); free($3); }
+        | '|' LINE '\n' { char* s = lineWithBreak($2); DESTROY_QUEUE(LineQueue, lineQ); APPEND_QUEUE(LineQueue, lineQ, s); free($2); }
 references:
           references reference break
         | /* empty */

src/xml.c

@@ -83,6 +83,8 @@ formatElementsToXML(
             xmlNodePtr em = xmlNewNode(sermon_ns, "em");
             formatElementsToXML(sermon_ns, em, a[i].elementContent.nestedContent, a[i].elementContentLength, numReferences, sermonReferencesPtr);
             xmlAddChild(parentElement, em);
+        } else if (a[i].elementType == FORMAT_BR) {
+            xmlAddChild(parentElement, xmlNewNode(sermon_ns, "br"));
         } else if (a[i].elementType == FORMAT_TEXT) {
             xmlAddChild(parentElement, xmlNewText(a[i].elementContent.textContent));
         } else if (a[i].elementType == FORMAT_GREEK) {

src/xslt.c

@@ -1,4 +1,5 @@
 #include <stdio.h>
+#include <stdlib.h>
 #include <string.h>
 #include <libxml/tree.h>
 #include <libxslt/xslt.h>