Bump version, ensure manpage comes along

TODO: No indentation on first line

.gitignore

@@ -2,6 +2,7 @@ Makefile
 Makefile.in
 aclocal.m4
 autom4te.cache/
+compile
 config.h
 config.h.in
 config.h.in~
@@ -22,3 +23,4 @@ stamp-h1
 ylwrap
 *.o
 *.core
+*.tar.gz

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.
@@ -46,4 +46,4 @@ The markup syntax is very simple:
         > This paragraph will be
         > a block quote.
 
-  - Text enclosed between `[* starred braces *]` will be ignored as a comment.
+  - Text enclosed between `[* starred braces *]` will be ignored as a comment.

configure.ac

@@ -2,13 +2,13 @@
 # Process this file with autoconf to produce a configure script.
 
 AC_PREREQ([2.69])
-AC_INIT([sermon], [1.0], [david.a.baer@gmail.com])
+AC_INIT([sermon], [1.4], [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">

sermon.1

@@ -0,0 +1,48 @@
+.Dd $Mdocdate: July 7 2016$
+.Dt SERMON 1
+.Os
+.Sh NAME
+.Nm sermon
+.Nd converts sermon text markup to a variety of formats
+.Sh SYNOPSIS
+.Nm sermon
+.Op Fl hv
+.Op Fl a Ar author
+.Op Fl s Ar stylename
+.Op Fl o Ar output
+.Ar
+.Sh DESCRIPTION
+The
+.Nm
+utility converts sermon markup text into a variety of useful formats,
+including
+.Em HTML Ns
+,
+.Em ODT Ns
+, and
+.Em XSL-FO No Ns .
+.\" .Sh CONTEXT
+.\" For section 9 functions only.
+.\" .Sh IMPLEMENTATION NOTES
+.\" Not used in OpenBSD.
+.\" .Sh RETURN VALUES
+.\" For sections 2, 3, and 9 function return values only.
+.\" .Sh ENVIRONMENT
+.\" For sections 1, 6, 7, and 8 only.
+.\" .Sh FILES
+.\" .Sh EXIT STATUS
+.\" For sections 1, 6, and 8 only.
+.\" .Sh EXAMPLES
+.\" .Sh DIAGNOSTICS
+.\" For sections 1, 4, 6, 7, 8, and 9 printf/stderr messages only.
+.\" .Sh ERRORS
+.\" For sections 2, 3, 4, and 9 errno settings only.
+.\" .Sh SEE ALSO
+.\" .Xr foobar 1
+.\" .Sh STANDARDS
+.\" .Sh HISTORY
+.\" .Sh AUTHORS
+.\" .Sh CAVEATS
+.\" .Sh BUGS
+.\" .Sh SECURITY CONSIDERATIONS
+.\" Not used in OpenBSD.

src/format.c

@@ -44,6 +44,8 @@ typedef enum {
     TOK_UNICODE,
     TOK_STAR,
     TOK_REF,
+    TOK_URL,
+    TOK_BREAK,
     /*
     TOK_DASH,
     TOK_OPEN_DOUBLE_QUOTE,
@@ -68,22 +70,37 @@ 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);
 }
 
+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 + 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] == '/'))));
+}
+
 static Token
 nextToken(Tokenizer tokenizer) {
     int startIndex = tokenizer->byteIndex;
@@ -99,6 +116,11 @@ 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 == '.'))) {
@@ -125,12 +147,30 @@ nextToken(Tokenizer tokenizer) {
         result.toktype = TOK_REF;
         result.toktext = strndup(tokenizer->txt + idStart, idEnd - idStart);
         return result;
+    } else if (httpAt(tokenizer)) {
+        int endIndex = 0;
+        while ((ch != 0) && (ch != ' ') && (ch != '\r') && (ch != '\n')) {
+            utf8Advance(tokenizer);
+            ch = utf8CharAt(tokenizer);
+        }
+        if (tokenizer->txt[tokenizer->byteIndex - 1] == '.') {
+            /* heuristic: url doesn't end in . */
+            endIndex = --tokenizer->byteIndex;
+        } else {
+            endIndex = tokenizer->byteIndex;
+        }
+
+        result.toktype = TOK_URL;
+        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 == '^') {
                 if (tokenizer->txt[tokenizer->byteIndex + 1] == '{') break;
+            } else if (httpAt(tokenizer)) {
+                break;
             }
         }
         result.toktype = TOK_TEXT;
@@ -172,6 +212,10 @@ 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 } } ;
@@ -181,6 +225,8 @@ int formatText(const char* txt, FormatElement** dst, CitationRecordQueue* citati
                 t = FORMAT_GREEK;
             } else if (tok.toktype == TOK_UNICODE) {
                 t = FORMAT_UNICODE;
+            } else if (tok.toktype == TOK_URL) {
+                t = FORMAT_URL;
             } else if (tok.toktype == TOK_REF) {
                 t = FORMAT_CITATION;
                 if (citationQPtr && !lookupCitation(*citationQPtr, tok.toktext)) {
@@ -223,15 +269,3 @@ void freeFormatElementArray(FormatElement* a, int length) {
     free(a);
 }
 
-#ifdef FORMATTER_TEST
-#include <stdio.h>
-
-const char* str = "My name in Chinese is \xe7\x86\x8a\xe5\xa4\xa7\xe8\xa1\x9b, or *xiong da wei*.  My favorite Greek passage is \xe1\xbc\x90\xce\xbd \xe1\xbc\x80\xcf\x81\xcf\x87\xe1\xbf\x87 \xe1\xbc\xa6\xce\xbd \xe1\xbd\x81 \xce\xbb\xe1\xbd\xb9\xce\xb3\xce\xbf\xcf\x82.^{cite}";
-
-int
-main() {
-    FormatElement* lst;
-    int l = formatText(str, &lst, NULL);
-    return 0;
-}
-#endif

src/format.h

@@ -34,10 +34,12 @@
 typedef enum {
     FORMAT_TEXT,
     FORMAT_EM,
+    FORMAT_BR,
     FORMAT_STRONG,
     FORMAT_CITATION,
     FORMAT_GREEK,
-    FORMAT_UNICODE
+    FORMAT_UNICODE,
+    FORMAT_URL
 } FormatElementType;
 
 typedef struct FormatElement FormatElement;

src/odt.c

@@ -73,7 +73,7 @@ createOutputDocument(const char* const outputFilename, const char* const tempDir
     if ((child_pid = fork()) == 0) {
         /* you are the child */
         char outputRealPath[FILENAME_MAX];
-        char* const args[] = { "zip", "-r", outputRealPath, ".", NULL };
+        char* const args[] = { "zip", "-r", outputRealPath, "mimetype", ".", NULL };
         realpath(outputFilename, outputRealPath);
         chdir(tempDir);
         freopen("/dev/null", "w", stdout);

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]*
@@ -23,14 +24,23 @@ ID                           [A-Za-z_][A-Za-z_0-9]*
 <REFERENCEINTRO>ref          { yylloc.first_column = yylloc.last_column + 1; yylloc.last_column = yylloc.first_column + 2; return KW_REF; }
 <REFERENCEINTRO>:            { BEGIN(REFERENCENAME); yylloc.first_column = ++yylloc.last_column; return ':'; }
 <REFERENCENAME>{ID}          { yylloc.first_column = yylloc.last_column + 1; yylloc.last_column = yylloc.first_column + strlen(yytext) + 1; yylval.sval = strdup(yytext); return ID; }
-<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; }
+<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 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; }
+<<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/utf8.c

@@ -73,7 +73,7 @@ uint32_t utf8CharAt(const utf8iterator* iter) {
                ((uint32_t)(iter->txt[byteIndex] & 0x03) << 24);
 
     } else if (((iter->txt[byteIndex] & 0xf7) == 0xfc) &&
-               ((iter->txt[byteIndex + 1]) & 0xc0 == 0x80) &&
+               ((iter->txt[byteIndex + 1] & 0xc0) == 0x80) &&
                ((iter->txt[byteIndex + 2] & 0xc0) == 0x80) &&
                ((iter->txt[byteIndex + 3] & 0xc0) == 0x80) &&
                ((iter->txt[byteIndex + 4] & 0xc0) == 0x80) &&
@@ -112,7 +112,7 @@ _next_offset(const utf8iterator* iter) {
                ((iter->txt[byteIndex + 4] & 0xc0) == 0x80)) {
         return 5;
     } else if (((iter->txt[byteIndex] & 0xf7) == 0xfc) &&
-               ((iter->txt[byteIndex + 1]) & 0xc0 == 0x80) &&
+               ((iter->txt[byteIndex + 1] & 0xc0) == 0x80) &&
                ((iter->txt[byteIndex + 2] & 0xc0) == 0x80) &&
                ((iter->txt[byteIndex + 3] & 0xc0) == 0x80) &&
                ((iter->txt[byteIndex + 4] & 0xc0) == 0x80) &&

src/xml.c

@@ -1,3 +1,31 @@
+/*
+ * xml.c - Create XML representation of sermon document
+ * Copyright © 2017 David A. Baer
+ * All rights reserved.
+ * 
+ * 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.
+ * 3. Neither the name of the organization nor the names of its contributors
+ *    may be used to endorse or promote products derived from this software
+ *    without specific prior written permission.
+ * 
+ * THIS SOFTWARE IS PROVIDED BY David A. Baer ''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 David A. Baer 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.
+ * 
+ */
 #include <libxml/tree.h>
 #include <string.h>
 #include "options.h"
@@ -55,6 +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) {
@@ -65,6 +95,11 @@ formatElementsToXML(
             xmlNodePtr unicode = xmlNewNode(sermon_ns, "unicode");
             xmlAddChild(unicode, xmlNewText(a[i].elementContent.textContent));
             xmlAddChild(parentElement, unicode);
+        } else if (a[i].elementType == FORMAT_URL) {
+            xmlNodePtr link = xmlNewNode(sermon_ns, "link");
+            xmlSetProp(link, "href", a[i].elementContent.textContent);
+            xmlAddChild(link, xmlNewText(a[i].elementContent.textContent));
+            xmlAddChild(parentElement, link);
         } else if (a[i].elementType == FORMAT_CITATION) {
             xmlNodePtr cite = xmlNewNode(sermon_ns, "cite");
             int num = findReferenceNumber(numReferences, sermonReferencesPtr, a[i].elementContent.textContent);

src/xml.h

@@ -1,3 +1,31 @@
+/*
+ * xml.h - create XML representation of sermon document
+ * Copyright © 2017 David A. Baer
+ * All rights reserved.
+ * 
+ * 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.
+ * 3. Neither the name of the organization nor the names of its contributors
+ *    may be used to endorse or promote products derived from this software
+ *    without specific prior written permission.
+ * 
+ * THIS SOFTWARE IS PROVIDED BY David A. Baer ''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 David A. Baer 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.
+ * 
+ */
 #ifndef _XML_H
 #define _XML_H