wikitext 3.0.1 → 3.1

data/ext/parser.c

@@ -1,4 +1,4 @@
-// Copyright 2007-2012 Wincent Colaiuta. All rights reserved.
+// Copyright 2007-2013 Wincent Colaiuta. All rights reserved.
 //
 // Redistribution and use in source and binary forms, with or without
 // modification, are permitted provided that the following conditions are met:
@@ -279,6 +279,160 @@ void wiki_downcase_bang(char *ptr, long len)
     }
 }
 
+void wiki_append_entity_from_utf32_char(str_t *output, uint32_t character)
+{
+    char hex_string[8]  = { '&', '#', 'x', 0, 0, 0, 0, ';' };
+    char scratch        = (character & 0xf000) >> 12;
+    hex_string[3]       = (scratch <= 9 ? scratch + 48 : scratch + 87);
+    scratch             = (character & 0x0f00) >> 8;
+    hex_string[4]       = (scratch <= 9 ? scratch + 48 : scratch + 87);
+    scratch             = (character & 0x00f0) >> 4;
+    hex_string[5]       = (scratch <= 9 ? scratch + 48 : scratch + 87);
+    scratch             = character & 0x000f;
+    hex_string[6]       = (scratch <= 9 ? scratch + 48 : scratch + 87);
+    str_append(output, hex_string, sizeof(hex_string));
+}
+
+// Convert a single UTF-8 codepoint to UTF-32
+//
+// Expects an input buffer, src, containing a UTF-8 encoded character (which
+// may be multi-byte). The end of the input buffer, end, is also passed in to
+// allow the detection of invalidly truncated codepoints. The number of bytes
+// in the UTF-8 character (between 1 and 4) is returned by reference in
+// width_out.
+//
+// Raises a RangeError if the supplied character is invalid UTF-8.
+uint32_t wiki_utf8_to_utf32(char *src, char *end, long *width_out)
+{
+    uint32_t dest = 0;
+    if ((unsigned char)src[0] <= 0x7f)
+    {
+        // ASCII
+        dest = src[0];
+        *width_out = 1;
+    }
+    else if ((src[0] & 0xe0) == 0xc0)
+    {
+        // byte starts with 110..... : this should be a two-byte sequence
+        if (src + 1 >= end)
+            // no second byte
+            rb_raise(eWikitextParserError, "invalid encoding: truncated byte sequence");
+        else if (((unsigned char)src[0] == 0xc0) ||
+                ((unsigned char)src[0] == 0xc1))
+            // overlong encoding: lead byte of 110..... but code point <= 127
+            rb_raise(eWikitextParserError, "invalid encoding: overlong encoding");
+        else if ((src[1] & 0xc0) != 0x80 )
+            // should have second byte starting with 10......
+            rb_raise(eWikitextParserError, "invalid encoding: malformed byte sequence");
+
+        dest =
+            ((uint32_t)(src[0] & 0x1f)) << 6 |
+            (src[1] & 0x3f);
+        *width_out = 2;
+    }
+    else if ((src[0] & 0xf0) == 0xe0)
+    {
+        // byte starts with 1110.... : this should be a three-byte sequence
+        if (src + 2 >= end)
+            // missing second or third byte
+            rb_raise(eWikitextParserError, "invalid encoding: truncated byte sequence");
+        else if (((src[1] & 0xc0) != 0x80 ) ||
+                ((src[2] & 0xc0) != 0x80 ))
+            // should have second and third bytes starting with 10......
+            rb_raise(eWikitextParserError, "invalid encoding: malformed byte sequence");
+
+        dest =
+            ((uint32_t)(src[0] & 0x0f)) << 12 |
+            ((uint32_t)(src[1] & 0x3f)) << 6 |
+            (src[2] & 0x3f);
+        *width_out = 3;
+    }
+    else if ((src[0] & 0xf8) == 0xf0)
+    {
+        // bytes starts with 11110... : this should be a four-byte sequence
+        if (src + 3 >= end)
+            // missing second, third, or fourth byte
+            rb_raise(eWikitextParserError, "invalid encoding: truncated byte sequence");
+        else if ((unsigned char)src[0] >= 0xf5 &&
+                (unsigned char)src[0] <= 0xf7)
+            // disallowed by RFC 3629 (codepoints above 0x10ffff)
+            rb_raise(eWikitextParserError, "invalid encoding: overlong encoding");
+        else if (((src[1] & 0xc0) != 0x80 ) ||
+                ((src[2] & 0xc0) != 0x80 ) ||
+                ((src[3] & 0xc0) != 0x80 ))
+            // should have second and third bytes starting with 10......
+            rb_raise(eWikitextParserError, "invalid encoding: malformed byte sequence");
+
+        dest =
+            ((uint32_t)(src[0] & 0x07)) << 18 |
+            ((uint32_t)(src[1] & 0x3f)) << 12 |
+            ((uint32_t)(src[1] & 0x3f)) << 6 |
+            (src[2] & 0x3f);
+        *width_out = 4;
+    }
+    else
+        rb_raise(eWikitextParserError, "invalid encoding: unexpected byte");
+    return dest;
+}
+
+// - non-printable (non-ASCII) characters converted to numeric entities
+// - QUOT and AMP characters converted to named entities
+// - if trim is true, leading and trailing whitespace trimmed
+// - if trim is false, there is no special treatment of spaces
+void wiki_append_sanitized_link_target(str_t *link_target, str_t *output, bool trim)
+{
+    char    *src        = link_target->ptr;
+    char    *start      = src;                          // remember this so we can check if we're at the start
+    char    *non_space  = output->ptr + output->len;    // remember last non-space character output
+    char    *end        = src + link_target->len;
+    while (src < end)
+    {
+        // need at most 8 bytes to display each input character (&#x0000;)
+        if (output->ptr + output->len + 8 > output->ptr + output->capacity) // outgrowing buffer, must grow
+        {
+            char *old_ptr = output->ptr;
+            str_grow(output, output->len + (end - src) * 8);    // allocate enough for worst case
+            if (old_ptr != output->ptr) // may have moved
+                non_space += output->ptr - old_ptr;
+        }
+
+        if (*src == '"')
+        {
+            char quot_entity_literal[] = { '&', 'q', 'u', 'o', 't', ';' };  // no trailing NUL
+            str_append(output, quot_entity_literal, sizeof(quot_entity_literal));
+        }
+        else if (*src == '&')
+        {
+            char amp_entity_literal[] = { '&', 'a', 'm', 'p', ';' };    // no trailing NUL
+            str_append(output, amp_entity_literal, sizeof(amp_entity_literal));
+        }
+        else if (*src == '<' || *src == '>')
+            rb_raise(rb_eRangeError, "invalid link text (\"%c\" may not appear in link text)", *src);
+        else if (*src == ' ' && src == start && trim)
+            start++;                            // we eat leading space
+        else if (*src >= 0x20 && *src <= 0x7e)  // printable ASCII
+        {
+            *(output->ptr + output->len) = *src;
+            output->len++;
+        }
+        else    // all others: must convert to entities
+        {
+            long        width;
+            wiki_append_entity_from_utf32_char(output, wiki_utf8_to_utf32(src, end, &width));
+            src         += width;
+            non_space   = output->ptr + output->len;
+            continue;
+        }
+        if (*src != ' ')
+            non_space = output->ptr + output->len;
+        src++;
+    }
+
+    // trim trailing space if necessary
+    if (trim && output->ptr + output->len != non_space)
+        output->len -= (output->ptr + output->len) - non_space;
+}
+
 // prepare hyperlink and append it to parser->output
 // if check_autolink is true, checks parser->autolink to decide whether to emit a real hyperlink
 // or merely the literal link target
@@ -286,13 +440,13 @@ void wiki_downcase_bang(char *ptr, long len)
 void wiki_append_hyperlink(parser_t *parser, VALUE link_prefix, str_t *link_target, str_t *link_text, VALUE link_class, VALUE link_rel, bool check_autolink)
 {
     if (check_autolink && !parser->autolink)
-        str_append_str(parser->output, link_target);
+        wiki_append_sanitized_link_target(link_target, parser->output, true);
     else
     {
         str_append(parser->output, a_start, sizeof(a_start) - 1);               // <a href="
         if (!NIL_P(link_prefix))
             str_append_string(parser->output, link_prefix);
-        str_append_str(parser->output, link_target);
+        wiki_append_sanitized_link_target(link_target, parser->output, true);
 
         // special handling for mailto URIs
         const char *mailto = "mailto:";
@@ -315,7 +469,7 @@ void wiki_append_hyperlink(parser_t *parser, VALUE link_prefix, str_t *link_targ
         }
         str_append(parser->output, a_start_close, sizeof(a_start_close) - 1);   // ">
         if (!link_text || link_text->len == 0) // re-use link_target
-            str_append_str(parser->output, link_target);
+            wiki_append_sanitized_link_target(link_target, parser->output, true);
         else
             str_append_str(parser->output, link_text);
         str_append(parser->output, a_end, sizeof(a_end) - 1);                   // </a>
@@ -649,102 +803,6 @@ void wiki_pop_excess_elements(parser_t *parser)
     }
 }
 
-// Convert a single UTF-8 codepoint to UTF-32
-//
-// Expects an input buffer, src, containing a UTF-8 encoded character (which
-// may be multi-byte). The end of the input buffer, end, is also passed in to
-// allow the detection of invalidly truncated codepoints. The number of bytes
-// in the UTF-8 character (between 1 and 4) is returned by reference in
-// width_out.
-//
-// Raises a RangeError if the supplied character is invalid UTF-8.
-uint32_t wiki_utf8_to_utf32(char *src, char *end, long *width_out)
-{
-    uint32_t dest;
-    if ((unsigned char)src[0] <= 0x7f)
-    {
-        // ASCII
-        dest = src[0];
-        *width_out = 1;
-    }
-    else if ((src[0] & 0xe0) == 0xc0)
-    {
-        // byte starts with 110..... : this should be a two-byte sequence
-        if (src + 1 >= end)
-            // no second byte
-            rb_raise(eWikitextParserError, "invalid encoding: truncated byte sequence");
-        else if (((unsigned char)src[0] == 0xc0) ||
-                ((unsigned char)src[0] == 0xc1))
-            // overlong encoding: lead byte of 110..... but code point <= 127
-            rb_raise(eWikitextParserError, "invalid encoding: overlong encoding");
-        else if ((src[1] & 0xc0) != 0x80 )
-            // should have second byte starting with 10......
-            rb_raise(eWikitextParserError, "invalid encoding: malformed byte sequence");
-
-        dest =
-            ((uint32_t)(src[0] & 0x1f)) << 6 |
-            (src[1] & 0x3f);
-        *width_out = 2;
-    }
-    else if ((src[0] & 0xf0) == 0xe0)
-    {
-        // byte starts with 1110.... : this should be a three-byte sequence
-        if (src + 2 >= end)
-            // missing second or third byte
-            rb_raise(eWikitextParserError, "invalid encoding: truncated byte sequence");
-        else if (((src[1] & 0xc0) != 0x80 ) ||
-                ((src[2] & 0xc0) != 0x80 ))
-            // should have second and third bytes starting with 10......
-            rb_raise(eWikitextParserError, "invalid encoding: malformed byte sequence");
-
-        dest =
-            ((uint32_t)(src[0] & 0x0f)) << 12 |
-            ((uint32_t)(src[1] & 0x3f)) << 6 |
-            (src[2] & 0x3f);
-        *width_out = 3;
-    }
-    else if ((src[0] & 0xf8) == 0xf0)
-    {
-        // bytes starts with 11110... : this should be a four-byte sequence
-        if (src + 3 >= end)
-            // missing second, third, or fourth byte
-            rb_raise(eWikitextParserError, "invalid encoding: truncated byte sequence");
-        else if ((unsigned char)src[0] >= 0xf5 &&
-                (unsigned char)src[0] <= 0xf7)
-            // disallowed by RFC 3629 (codepoints above 0x10ffff)
-            rb_raise(eWikitextParserError, "invalid encoding: overlong encoding");
-        else if (((src[1] & 0xc0) != 0x80 ) ||
-                ((src[2] & 0xc0) != 0x80 ) ||
-                ((src[3] & 0xc0) != 0x80 ))
-            // should have second and third bytes starting with 10......
-            rb_raise(eWikitextParserError, "invalid encoding: malformed byte sequence");
-
-        dest =
-            ((uint32_t)(src[0] & 0x07)) << 18 |
-            ((uint32_t)(src[1] & 0x3f)) << 12 |
-            ((uint32_t)(src[1] & 0x3f)) << 6 |
-            (src[2] & 0x3f);
-        *width_out = 4;
-    }
-    else
-        rb_raise(eWikitextParserError, "invalid encoding: unexpected byte");
-    return dest;
-}
-
-void wiki_append_entity_from_utf32_char(str_t *output, uint32_t character)
-{
-    char hex_string[8]  = { '&', '#', 'x', 0, 0, 0, 0, ';' };
-    char scratch        = (character & 0xf000) >> 12;
-    hex_string[3]       = (scratch <= 9 ? scratch + 48 : scratch + 87);
-    scratch             = (character & 0x0f00) >> 8;
-    hex_string[4]       = (scratch <= 9 ? scratch + 48 : scratch + 87);
-    scratch             = (character & 0x00f0) >> 4;
-    hex_string[5]       = (scratch <= 9 ? scratch + 48 : scratch + 87);
-    scratch             = character & 0x000f;
-    hex_string[6]       = (scratch <= 9 ? scratch + 48 : scratch + 87);
-    str_append(output, hex_string, sizeof(hex_string));
-}
-
 // trim parser->link_text in place
 void wiki_trim_link_text(parser_t *parser)
 {
@@ -772,72 +830,13 @@ void wiki_trim_link_text(parser_t *parser)
     }
 }
 
-// - non-printable (non-ASCII) characters converted to numeric entities
-// - QUOT and AMP characters converted to named entities
-// - if trim is true, leading and trailing whitespace trimmed
-// - if trim is false, there is no special treatment of spaces
-void wiki_append_sanitized_link_target(parser_t *parser, str_t *output, bool trim)
-{
-    char    *src        = parser->link_target->ptr;
-    char    *start      = src;                          // remember this so we can check if we're at the start
-    char    *non_space  = output->ptr + output->len;    // remember last non-space character output
-    char    *end        = src + parser->link_target->len;
-    while (src < end)
-    {
-        // need at most 8 bytes to display each input character (&#x0000;)
-        if (output->ptr + output->len + 8 > output->ptr + output->capacity) // outgrowing buffer, must grow
-        {
-            char *old_ptr = output->ptr;
-            str_grow(output, output->len + (end - src) * 8);    // allocate enough for worst case
-            if (old_ptr != output->ptr) // may have moved
-                non_space += output->ptr - old_ptr;
-        }
-
-        if (*src == '"')
-        {
-            char quot_entity_literal[] = { '&', 'q', 'u', 'o', 't', ';' };  // no trailing NUL
-            str_append(output, quot_entity_literal, sizeof(quot_entity_literal));
-        }
-        else if (*src == '&')
-        {
-            char amp_entity_literal[] = { '&', 'a', 'm', 'p', ';' };    // no trailing NUL
-            str_append(output, amp_entity_literal, sizeof(amp_entity_literal));
-        }
-        else if (*src == '<' || *src == '>')
-            rb_raise(rb_eRangeError, "invalid link text (\"%c\" may not appear in link text)", *src);
-        else if (*src == ' ' && src == start && trim)
-            start++;                            // we eat leading space
-        else if (*src >= 0x20 && *src <= 0x7e)  // printable ASCII
-        {
-            *(output->ptr + output->len) = *src;
-            output->len++;
-        }
-        else    // all others: must convert to entities
-        {
-            long        width;
-            wiki_append_entity_from_utf32_char(output, wiki_utf8_to_utf32(src, end, &width));
-            src         += width;
-            non_space   = output->ptr + output->len;
-            continue;
-        }
-        if (*src != ' ')
-            non_space = output->ptr + output->len;
-        src++;
-    }
-
-    // trim trailing space if necessary
-    if (trim && output->ptr + output->len != non_space)
-        output->len -= (output->ptr + output->len) - non_space;
-}
-
 VALUE Wikitext_parser_sanitize_link_target(VALUE self, VALUE string)
 {
-    parser_t parser;
-    parser.link_target = str_new_from_string(string);
-    GC_WRAP_STR(parser.link_target, link_target_gc);
+    str_t *link_target = str_new_from_string(string);
+    GC_WRAP_STR(link_target, link_target_gc);
     str_t *output = str_new();
     GC_WRAP_STR(output, output_gc);
-    wiki_append_sanitized_link_target(&parser, output, true);
+    wiki_append_sanitized_link_target(link_target, output, true);
     return string_from_str(output);
 }
 
@@ -950,7 +949,7 @@ void wiki_rollback_failed_internal_link(parser_t *parser)
     str_append(parser->output, link_start, sizeof(link_start) - 1);
     if (parser->link_target->len > 0)
     {
-        wiki_append_sanitized_link_target(parser, parser->output, false);
+        wiki_append_sanitized_link_target(parser->link_target, parser->output, false);
         if (scope_includes_separator)
         {
             str_append(parser->output, separator, sizeof(separator) - 1);
@@ -1009,6 +1008,7 @@ VALUE Wikitext_parser_initialize(int argc, VALUE *argv, VALUE self)
     VALUE external_link_class           = rb_str_new2("external");
     VALUE external_link_rel             = Qnil;
     VALUE mailto_class                  = rb_str_new2("mailto");
+    VALUE link_proc                     = Qnil;
     VALUE internal_link_prefix          = rb_str_new2("/wiki/");
     VALUE img_prefix                    = rb_str_new2("/images/");
     VALUE output_style                  = ID2SYM(rb_intern("html"));
@@ -1026,6 +1026,7 @@ VALUE Wikitext_parser_initialize(int argc, VALUE *argv, VALUE self)
         external_link_class             = OVERRIDE_IF_SET(external_link_class);
         external_link_rel               = OVERRIDE_IF_SET(external_link_rel);
         mailto_class                    = OVERRIDE_IF_SET(mailto_class);
+        link_proc                       = OVERRIDE_IF_SET(link_proc);
         internal_link_prefix            = OVERRIDE_IF_SET(internal_link_prefix);
         img_prefix                      = OVERRIDE_IF_SET(img_prefix);
         output_style                    = OVERRIDE_IF_SET(output_style);
@@ -1040,6 +1041,7 @@ VALUE Wikitext_parser_initialize(int argc, VALUE *argv, VALUE self)
     rb_iv_set(self, "@external_link_class",             external_link_class);
     rb_iv_set(self, "@external_link_rel",               external_link_rel);
     rb_iv_set(self, "@mailto_class",                    mailto_class);
+    rb_iv_set(self, "@link_proc",                       link_proc);
     rb_iv_set(self, "@internal_link_prefix",            internal_link_prefix);
     rb_iv_set(self, "@img_prefix",                      img_prefix);
     rb_iv_set(self, "@output_style",                    output_style);
@@ -1084,6 +1086,7 @@ VALUE Wikitext_parser_parse(int argc, VALUE *argv, VALUE self)
     link_class          = NIL_P(link_class) ? Qnil : StringValue(link_class);
     VALUE link_rel      = rb_iv_get(self, "@external_link_rel");
     link_rel            = NIL_P(link_rel) ? Qnil : StringValue(link_rel);
+    VALUE link_proc     = rb_iv_get(self, "@link_proc");
     VALUE mailto_class  = rb_iv_get(self, "@mailto_class");
     mailto_class        = NIL_P(mailto_class) ? Qnil : StringValue(mailto_class);
     VALUE prefix        = rb_iv_get(self, "@internal_link_prefix");
@@ -1092,7 +1095,6 @@ VALUE Wikitext_parser_parse(int argc, VALUE *argv, VALUE self)
     // process options hash
     int base_indent = 0;
     int base_heading_level = NUM2INT(rb_iv_get(self, "@base_heading_level"));
-    VALUE link_proc = Qnil;
     if (!NIL_P(options) && TYPE(options) == T_HASH)
     {
         // :indent => 0 (or more)
@@ -1979,9 +1981,13 @@ VALUE Wikitext_parser_parse(int argc, VALUE *argv, VALUE self)
 
             case URI:
                 if (IN(NO_WIKI_START))
+                {
                     // user can temporarily suppress autolinking by using <nowiki></nowiki>
                     // note that unlike MediaWiki, we do allow autolinking inside PRE blocks
-                    str_append(parser->output, token->start, TOKEN_LEN(token));
+                    token_str->ptr = token->start;
+                    token_str->len = TOKEN_LEN(token);
+                    wiki_append_sanitized_link_target(token_str, parser->output, false);
+                }
                 else if (IN(LINK_START))
                 {
                     // if the URI were allowed it would have been handled already in LINK_START
@@ -2018,7 +2024,11 @@ VALUE Wikitext_parser_parse(int argc, VALUE *argv, VALUE self)
                         }
                     }
                     else
-                        str_append(parser->link_text, token->start, TOKEN_LEN(token));
+                    {
+                        token_str->ptr = token->start;
+                        token_str->len = TOKEN_LEN(token);
+                        wiki_append_sanitized_link_target(token_str, parser->link_text, false);
+                    }
                 }
                 else
                 {
@@ -2213,7 +2223,7 @@ VALUE Wikitext_parser_parse(int argc, VALUE *argv, VALUE self)
                     {
                         // use link target as link text
                         str_clear(parser->link_text);
-                        wiki_append_sanitized_link_target(parser, parser->link_text, true);
+                        wiki_append_sanitized_link_target(parser->link_target, parser->link_text, true);
                     }
                     else
                         wiki_trim_link_text(parser);

data/ext/wikitext.c

@@ -1,4 +1,4 @@
-// Copyright 2008-2009 Wincent Colaiuta. All rights reserved.
+// Copyright 2008-2013 Wincent Colaiuta. All rights reserved.
 //
 // Redistribution and use in source and binary forms, with or without
 // modification, are permitted provided that the following conditions are met:
@@ -80,6 +80,7 @@ void Init_wikitext()
     rb_define_attr(cWikitextParser, "external_link_class", Qtrue, Qtrue);
     rb_define_attr(cWikitextParser, "external_link_rel", Qtrue, Qtrue);
     rb_define_attr(cWikitextParser, "mailto_class", Qtrue, Qtrue);
+    rb_define_attr(cWikitextParser, "link_proc", Qtrue, Qtrue);
     rb_define_attr(cWikitextParser, "autolink", Qtrue, Qtrue);
     rb_define_attr(cWikitextParser, "space_to_underscore", Qtrue, Qtrue);
     rb_define_attr(cWikitextParser, "minimum_fulltext_token_length", Qtrue, Qtrue);

data/lib/wikitext/version.rb

@@ -1,4 +1,4 @@
-# Copyright 2007-2012 Wincent Colaiuta. All rights reserved.
+# Copyright 2007-2013 Wincent Colaiuta. All rights reserved.
 #
 # Redistribution and use in source and binary forms, with or without
 # modification, are permitted provided that the following conditions are met:
@@ -22,5 +22,5 @@
 # POSSIBILITY OF SUCH DAMAGE.
 
 module Wikitext
-  VERSION = '3.0.1'
+  VERSION = '3.1'
 end # module Wikitext

data/spec/autolinking_spec.rb

@@ -1,4 +1,4 @@
-# Copyright 2007-2010 Wincent Colaiuta. All rights reserved.
+# Copyright 2007-2012 Wincent Colaiuta. All rights reserved.
 #
 # Redistribution and use in source and binary forms, with or without
 # modification, are permitted provided that the following conditions are met:
@@ -58,7 +58,12 @@ describe Wikitext::Parser, 'autolinking' do
       @parser.parse(uri).should == %Q{<p><a href="svn://example.com/" class="external">svn://example.com/</a></p>\n}
     end
 
-    it 'should apple the external_link_class CSS class if set' do
+    it 'converts ampersands into entities' do
+      expected = %{<p><a href="http://google.com/?q=1&amp;lang=en" class="external">http://google.com/?q=1&amp;lang=en</a></p>\n}
+      @parser.parse('http://google.com/?q=1&lang=en').should == expected
+    end
+
+    it 'should apply the external_link_class CSS class if set' do
       uri = 'http://example.com/'
       @parser.external_link_class = 'bar'
       @parser.parse(uri).should == %Q{<p><a href="http://example.com/" class="bar">http://example.com/</a></p>\n}

data/spec/external_link_spec.rb

@@ -75,7 +75,16 @@ describe Wikitext::Parser, 'external links' do
     # more general case of bug reported here: https://wincent.com/issues/1955
     expected = %{<p><a href="http://google.com/?q=user@example.com" class="external">Google for user@example.com</a></p>\n}
     @parser.parse('[http://google.com/?q=user@example.com Google for user@example.com]').should == expected
+  end
+
+  it 'formats ampersands in link targets using entities' do
+    expected =%{<p><a href="http://google.com/?q=1&amp;lang=en" class="external">Google</a></p>\n}
+    @parser.parse('[http://google.com/?q=1&lang=en Google]').should == expected
+  end
 
+  it 'formats ampersands in URIs in link text' do
+    expected =%{<p><a href="http://google.com/?q=1&amp;lang=en" class="external">http://google.com/?q=1&amp;lang=en</a></p>\n}
+    @parser.parse('[http://google.com/?q=1&lang=en http://google.com/?q=1&lang=en]').should == expected
   end
 
   it 'should format absolute path links' do

data/spec/internal_link_spec.rb

@@ -1,5 +1,5 @@
 # encoding: utf-8
-# Copyright 2007-2010 Wincent Colaiuta. All rights reserved.
+# Copyright 2007-2013 Wincent Colaiuta. All rights reserved.
 #
 # Redistribution and use in source and binary forms, with or without
 # modification, are permitted provided that the following conditions are met:
@@ -113,26 +113,41 @@ describe Wikitext::Parser, 'internal links (space to underscore off)' do
   end
 
   describe '"red link" support' do
-    it 'should accept a Proc object via the optional "link_proc" parameter' do
+    it 'accepts a Proc object via the optional "link_proc" parameter' do
       @parser.parse('foo', :link_proc => Proc.new { }).should == %Q{<p>foo</p>\n}
     end
 
-    it 'should accept a lambda via the optional "link_proc" parameter' do
+    it 'accepts a lambda via the optional "link_proc" parameter' do
       @parser.parse('foo', :link_proc => lambda { }).should == %Q{<p>foo</p>\n}
     end
 
-    it 'should apply custom link CSS when supplied (Proc object version)' do
+    it 'applies custom link CSS when supplied (Proc object version)' do
       link_proc = Proc.new { |target| target == 'bar' ? 'redlink' : nil }
       expected = %Q{<p><a href="/wiki/foo">foo</a> <a href="/wiki/bar" class="redlink">bar</a></p>\n}
       @parser.parse('[[foo]] [[bar]]', :link_proc => link_proc).should == expected
     end
 
-    it 'should apply custom link CSS when supplied (lambda version)' do
+    it 'applies custom link CSS when supplied (lambda version)' do
       link_proc = lambda { |target| target == 'bar' ? 'redlink' : nil }
       expected = %Q{<p><a href="/wiki/foo">foo</a> <a href="/wiki/bar" class="redlink">bar</a></p>\n}
       @parser.parse('[[foo]] [[bar]]', :link_proc => link_proc).should == expected
     end
 
+    it 'uses a lamba passed in when the Parser is initialized' do
+      link_proc = lambda { |target| target == 'bar' ? 'redlink' : nil }
+      parser = Wikitext::Parser.new :link_proc => link_proc
+      expected = %Q{<p><a href="/wiki/foo">foo</a> <a href="/wiki/bar" class="redlink">bar</a></p>\n}
+      parser.parse('[[foo]] [[bar]]').should == expected
+    end
+
+    it 'uses a lamba set as an attribute on the Parser' do
+      link_proc = lambda { |target| target == 'bar' ? 'redlink' : nil }
+      parser = Wikitext::Parser.new
+      parser.link_proc = link_proc
+      expected = %Q{<p><a href="/wiki/foo">foo</a> <a href="/wiki/bar" class="redlink">bar</a></p>\n}
+      parser.parse('[[foo]] [[bar]]').should == expected
+    end
+
     it 'should apply no custom link CSS when supplied nil (Proc object version)' do
       expected = %Q{<p><a href="/wiki/foo">foo</a></p>\n}
       @parser.parse('[[foo]]', :link_proc => Proc.new { |target| nil }).should == expected

data/spec/rails_spec.rb

@@ -0,0 +1,239 @@
+# Copyright 2009-2011 Wincent Colaiuta. 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.
+
+# THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "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 COPYRIGHT HOLDERS OR CONTRIBUTORS 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.
+
+require 'spec_helper'
+require 'wikitext/version'
+require 'fileutils'
+require 'pathname'
+require 'wopen3'
+
+module RailsSpecs
+  TRASH_PATH              = Pathname.new(__FILE__).dirname + '.trash'
+  AREL_CLONE_PATH         = TRASH_PATH + 'arel.git'
+  AREL_REPO               = 'git://github.com/rails/arel.git'
+  RAILS_CLONE_PATH        = TRASH_PATH + 'rails.git'
+  RAILS_REPO              = 'git://github.com/rails/rails.git'
+  WIKITEXT_GEM_PATH       = TRASH_PATH + '..' + '..'
+  SUCCESSFUL_TEST_RESULT  = /1 tests, 3 assertions, 0 failures, 0 errors/
+
+  def run cmd, *args
+    result = Wopen3.system(*([cmd] + args))
+    if result.status != 0
+      command_string = ([cmd] + args).join(' ')
+      puts "\n*** COMMAND #{command_string} EXITED WITH NON-ZERO EXIT STATUS (#{result.status})"
+      puts "*** STDOUT FOR COMMAND #{command_string}:", result.stdout
+      puts "*** STDERR FOR COMMAND #{command_string}:", result.stderr
+      raise "non-zero exit status (#{result.status}) for '#{command_string}'"
+    end
+    result
+  end
+
+  def clone repo, path
+    if File.exist? path
+      FileUtils.cd path do
+        run 'git', 'fetch'
+      end
+    else
+      run 'git', 'clone', repo, path
+    end
+  end
+
+  def app_path version
+    version = 'edge' if version.nil?
+    version = "v#{version}" if version =~ /\A\d\./
+    TRASH_PATH + "#{version}-app"
+  end
+
+  # if version is nil will create an "Edge" app
+  def create_rails3_app rails_version, arel_version = nil
+    app = app_path rails_version
+    clone AREL_REPO, AREL_CLONE_PATH
+    FileUtils.cd AREL_CLONE_PATH do
+      if arel_version
+        run 'git', 'reset', '--hard', "v#{arel_version}"
+      else # "Edge"
+        run 'git', 'reset', '--hard', 'origin/master'
+      end
+      run 'git', 'clean', '-f'
+    end
+
+    clone RAILS_REPO, RAILS_CLONE_PATH
+    FileUtils.cd RAILS_CLONE_PATH do
+      if rails_version
+        run 'git', 'reset', '--hard', "v#{rails_version}"
+      else # "Edge"
+        run 'git', 'reset', '--hard', 'origin/master'
+      end
+      run 'git', 'clean', '-f'
+
+      begin
+        clean_bundler_environment
+        run 'env', "AREL=#{AREL_CLONE_PATH}",
+            'bundle', 'install', '--path', '../bundle', '--without', 'db'
+        FileUtils.rm_r(app) if File.exist?(app)
+        run 'env', "AREL=#{AREL_CLONE_PATH}",
+            'bundle', 'exec', 'bin/rails', 'new', app, '--skip-activerecord', '--dev'
+      ensure
+        restore_bundler_environment
+      end
+    end
+
+    create_gemfile app
+    bundlerize app
+  end
+
+  def insert text, after, infile
+    output = []
+    found   = false
+    File.read(infile).split("\n").each do |line|
+      output << line
+      if found == false && line =~ /#{Regexp.escape(after)}/
+        found = true
+        output << text
+      end
+    end
+    File.open(infile, 'wb') { |f| f.write(output.join("\n")) }
+    raise "text '#{after}' not found" unless found
+  end
+
+  def add_text_to_routes text, infile
+    insert text, 'Application.routes.draw', infile
+  end
+
+  def create_gemfile app
+    File.open(app + 'Gemfile', 'w') do |f|
+      f.write <<-GEMFILE
+        source :rubygems
+        gem 'arel', :path => "#{AREL_CLONE_PATH.realpath}"
+        gem 'rake'
+        gem 'rails', :path => "#{RAILS_CLONE_PATH.realpath}"
+        gem 'sqlite3'
+        gem 'wikitext', :path => "#{WIKITEXT_GEM_PATH.realpath}"
+      GEMFILE
+    end
+  end
+
+  def bundlerize app
+    clean_bundler_environment
+    Dir.chdir app do
+      run 'bundle', 'install', '--path', '../bundle', '--binstubs'
+    end
+  ensure
+    restore_bundler_environment
+  end
+
+  def create_controller app
+    File.open(app + 'app' + 'controllers' + 'wiki_controller.rb', 'w') do |f|
+      f.write 'class WikiController < ApplicationController; end'
+    end
+  end
+
+  def create_template app
+    template_dir = app + 'app' + 'views' + 'wiki'
+    FileUtils.mkdir template_dir
+    File.open(template_dir + 'index.html.wikitext', 'w') do |f|
+      f.write '* hello, world!'
+    end
+  end
+
+  def create_test app
+    # integration tests won't run without a schema.rb
+    FileUtils.touch app + 'db' + 'schema.rb'
+
+    File.open(app + 'test' + 'integration' + 'wiki_test.rb', 'w') do |f|
+      f.write <<'TEST'
+require File.join(File.dirname(__FILE__), '..', 'test_helper')
+
+class WikiTest < ActionController::IntegrationTest
+  def test_wiki_index
+    get "/wiki"
+    assert_response :success
+    assert_template "wiki/index"
+    assert_select 'ul>li', 'hello, world!'
+  end
+end
+TEST
+      end
+  end
+
+  def update_routes app
+    routes = app + 'config' + 'routes.rb'
+    add_text_to_routes 'match "/wiki" => "wiki#index"', routes
+  end
+
+  def setup_rails_app rails_version = nil, arel_version = nil
+    create_rails3_app rails_version, arel_version
+    path = app_path rails_version
+    update_routes path
+    create_controller path
+    create_template path
+    create_test path
+  end
+
+  def clean_bundler_environment
+    @bundler_env = ENV.select { |key, value| key =~ /\A(BUNDLE|GEM)_/ }
+    @bundler_env.each { |pair| ENV.delete(pair.first) }
+  end
+
+  def restore_bundler_environment
+    @bundler_env.each { |pair| ENV[pair[0]] = pair[1] }
+  end
+
+  def run_integration_test app
+    clean_bundler_environment
+    FileUtils.cd app do
+      return run('bin/rake', 'test:integration').stdout
+    end
+  ensure
+    restore_bundler_environment
+  end
+end # module RailsSpecs
+
+# different versions of Rails require different versions of Arel
+{ '3.1.0' => '2.1.1' }.each do |rails_version, arel_version|
+  describe "Template handler in Rails #{rails_version}" do
+    include RailsSpecs
+
+    before :all do
+      setup_rails_app rails_version, arel_version
+      @path = app_path rails_version
+    end
+
+    it 'should process the template using the wikitext module' do
+      run_integration_test(@path).should =~ RailsSpecs::SUCCESSFUL_TEST_RESULT
+    end
+  end
+end
+
+describe 'Template handler in Edge Rails' do
+  include RailsSpecs
+
+  before :all do
+    setup_rails_app
+    @path = app_path nil
+  end
+
+  it 'should process the template using the wikitext module' do
+    run_integration_test(@path).should =~ RailsSpecs::SUCCESSFUL_TEST_RESULT
+  end
+end

metadata

@@ -4,9 +4,8 @@ version: !ruby/object:Gem::Version
   prerelease: false
   segments: 
   - 3
-  - 0
   - 1
-  version: 3.0.1
+  version: "3.1"
 platform: ruby
 authors: 
 - Wincent Colaiuta
@@ -14,10 +13,11 @@ autorequire:
 bindir: bin
 cert_chain: []
 
-date: 2012-03-03 00:00:00 -08:00
+date: 2013-02-16 00:00:00 -08:00
 default_executable: 
 dependencies: 
 - !ruby/object:Gem::Dependency 
+  type: :development
   version_requirements: &id001 !ruby/object:Gem::Requirement 
     requirements: 
     - - ">="
@@ -25,24 +25,24 @@ dependencies:
         segments: 
         - 0
         version: "0"
-  requirement: *id001
   name: rake
+  requirement: *id001
   prerelease: false
-  type: :development
 - !ruby/object:Gem::Dependency 
+  type: :development
   version_requirements: &id002 !ruby/object:Gem::Requirement 
     requirements: 
-    - - ~>
+    - - ">="
       - !ruby/object:Gem::Version 
         segments: 
         - 2
         - 0
         version: "2.0"
-  requirement: *id002
   name: rspec
+  requirement: *id002
   prerelease: false
-  type: :development
 - !ruby/object:Gem::Dependency 
+  type: :development
   version_requirements: &id003 !ruby/object:Gem::Requirement 
     requirements: 
     - - ">="
@@ -50,11 +50,11 @@ dependencies:
         segments: 
         - 0
         version: "0"
-  requirement: *id003
   name: thor
+  requirement: *id003
   prerelease: false
-  type: :development
 - !ruby/object:Gem::Dependency 
+  type: :development
   version_requirements: &id004 !ruby/object:Gem::Requirement 
     requirements: 
     - - ">="
@@ -64,11 +64,11 @@ dependencies:
         - 5
         - 8
         version: 0.5.8
-  requirement: *id004
   name: yard
+  requirement: *id004
   prerelease: false
-  type: :development
 - !ruby/object:Gem::Dependency 
+  type: :development
   version_requirements: &id005 !ruby/object:Gem::Requirement 
     requirements: 
     - - ">="
@@ -76,11 +76,11 @@ dependencies:
         segments: 
         - 0
         version: "0"
-  requirement: *id005
   name: wopen3
+  requirement: *id005
   prerelease: false
-  type: :development
 - !ruby/object:Gem::Dependency 
+  type: :development
   version_requirements: &id006 !ruby/object:Gem::Requirement 
     requirements: 
     - - ">="
@@ -88,10 +88,9 @@ dependencies:
         segments: 
         - 0
         version: "0"
-  requirement: *id006
   name: ZenTest
+  requirement: *id006
   prerelease: false
-  type: :development
 description: "    Wikitext is a fast wikitext-to-HTML translator written in C.\n"
 email: win@wincent.com
 executables: 
@@ -149,6 +148,7 @@ files:
 - spec/p_spec.rb
 - spec/parser_spec.rb
 - spec/pre_spec.rb
+- spec/rails_spec.rb
 - spec/regressions_spec.rb
 - spec/spec_helper.rb
 - spec/string_spec.rb