New module to parse a simple markup language

2000-10-24  Havoc Pennington  <hp@pobox.com>

        * gmarkup.h, gmarkup.c: New module to parse a simple
	markup language

	* Makefile.am: add gmarkup.h, gmarkup.c

	* tests/Makefile.am: add markup-test

	* gstring.h (g_string_new_len): new function to create a string
	with a length
	(g_string_new): avoid a gratuitous realloc

tests/Makefile.am

@@ -18,6 +18,7 @@ TESTS = \
 	gio-test	\
 	hash-test	\
 	list-test	\
+	markup-test	\
 	node-test	\
 	queue-test	\
 	rand-test	\
@@ -43,6 +44,7 @@ dirname_test_LDADD = $(progs_LDADD)
 gio_test_LDADD = $(progs_LDADD)
 hash_test_LDADD = $(progs_LDADD)
 list_test_LDADD = $(progs_LDADD)
+markup_test_LDADD = $(progs_LDADD)
 node_test_LDADD = $(progs_LDADD)
 queue_test_LDADD = $(progs_LDADD)
 rand_test_LDADD = $(progs_LDADD)

tests/markup-test.c

@@ -0,0 +1,202 @@
+#include <stdio.h>
+#include <glib.h>
+
+static int depth = 0;
+
+static void
+indent (int extra)
+{
+  int i = 0;
+  while (i < depth)
+    {
+      fputs ("  ", stdout);
+      ++i;
+    }
+}
+
+static void
+start_element_handler  (GMarkupParseContext *context,
+                        const gchar         *element_name,
+                        const gchar        **attribute_names,
+                        const gchar        **attribute_values,
+                        gpointer             user_data,
+                        GError             **error)
+{
+  int i;
+  
+  indent (0);
+  printf ("ELEMENT '%s'\n", element_name);
+
+  i = 0;
+  while (attribute_names[i] != NULL)
+    {
+      indent (1);
+
+      printf ("%s=\"%s\"\n",
+              attribute_names[i],
+              attribute_values[i]);
+      
+      ++i;
+    }
+  
+  ++depth;
+}
+
+static void
+end_element_handler    (GMarkupParseContext *context,
+                        const gchar         *element_name,
+                        gpointer             user_data,
+                        GError             **error)
+{
+  --depth;
+  indent (0);
+  printf ("END '%s'\n", element_name);
+}
+
+static void
+text_handler           (GMarkupParseContext *context,
+                        const gchar         *text,
+                        gint                 text_len,
+                        gpointer             user_data,
+                        GError             **error)
+{
+  indent (0);
+  printf ("TEXT '%s'\n", text);
+}
+
+
+static void
+passthrough_handler    (GMarkupParseContext *context,
+                        const gchar         *passthrough_text,
+                        gint                 text_len,
+                        gpointer             user_data,
+                        GError             **error)
+{
+  indent (0);
+
+  printf ("PASS '%s'\n", passthrough_text);
+}
+
+static void
+error_handler          (GMarkupParseContext *context,
+                        GError              *error,
+                        gpointer             user_data)
+{
+  fprintf (stderr, " %s\n", error->message);
+}
+
+static GMarkupParser parser = {
+  start_element_handler,
+  end_element_handler,
+  text_handler,
+  passthrough_handler,
+  error_handler
+};
+
+static int
+test_in_chunks (const gchar *contents,
+                gint         length,
+                gint         chunk_size)
+{
+  GMarkupParseContext *context;
+  int i = 0;
+  
+  context = g_markup_parse_context_new (&parser, 0, NULL, NULL);
+
+  while (i < length)
+    {
+      int this_chunk = MIN (length - i, chunk_size);
+
+      if (!g_markup_parse_context_parse (context,
+                                         contents + i,
+                                         this_chunk,
+                                         NULL))
+        {
+          g_markup_parse_context_free (context);
+          return 1;
+        }
+
+      i += this_chunk;
+    }
+      
+  if (!g_markup_parse_context_end_parse (context, NULL))
+    {
+      g_markup_parse_context_free (context);
+      return 1;
+    }
+
+  g_markup_parse_context_free (context);
+
+  return 0;
+}
+
+static int
+test_file (const gchar *filename)
+{
+  gchar *contents;
+  gint   length;
+  GError *error;
+  GMarkupParseContext *context;
+  
+  error = NULL;
+  if (!g_file_get_contents (filename,
+                            &contents,
+                            &length,
+                            &error))
+    {
+      fprintf (stderr, "%s\n", error->message);
+      g_error_free (error);
+      return 1;
+    }
+
+  context = g_markup_parse_context_new (&parser, 0, NULL, NULL);
+
+  if (!g_markup_parse_context_parse (context, contents, length, NULL))
+    {
+      g_markup_parse_context_free (context);
+      return 1;
+    }
+
+  if (!g_markup_parse_context_end_parse (context, NULL))
+    {
+      g_markup_parse_context_free (context);
+      return 1;
+    }
+
+  g_markup_parse_context_free (context);
+
+  /* A byte at a time */
+  if (test_in_chunks (contents, length, 1) != 0)
+    return 1;
+
+  /* 2 bytes */
+  if (test_in_chunks (contents, length, 2) != 0)
+    return 1;
+
+  /*5 bytes */
+  if (test_in_chunks (contents, length, 5) != 0)
+    return 1;
+  
+  /* 12 bytes */
+  if (test_in_chunks (contents, length, 12) != 0)
+    return 1;
+  
+  /* 1024 bytes */
+  if (test_in_chunks (contents, length, 1024) != 0)
+    return 1;
+
+  return 0;
+}
+
+int
+main (int   argc,
+      char *argv[])
+{
+  if (argc > 1)
+    return test_file (argv[1]);
+  else
+    {
+      fprintf (stderr, "Give a markup file on the command line\n");
+      return 1;
+    }
+}

tests/markups/fail-10.gmarkup

@@ -0,0 +1,2 @@
+<foo>
+</|foo>

tests/markups/fail-11.gmarkup

@@ -0,0 +1,4 @@
+<foo>
+<bar>
+</foo>
+</bar>

tests/markups/fail-12.gmarkup

@@ -0,0 +1 @@
+</foo>

tests/markups/fail-13.gmarkup

@@ -0,0 +1 @@
+</foo|>

tests/markups/fail-14.gmarkup

@@ -0,0 +1,2 @@
+<foo>
+<

tests/markups/fail-15.gmarkup

@@ -0,0 +1,3 @@
+<foo>
+<bar>
+</bar>

tests/markups/fail-16.gmarkup

@@ -0,0 +1 @@
+<foo/

tests/markups/fail-17.gmarkup

@@ -0,0 +1 @@
+<fo

tests/markups/fail-18.gmarkup

@@ -0,0 +1 @@
+<foo bar

tests/markups/fail-19.gmarkup

@@ -0,0 +1 @@
+<foo 

tests/markups/fail-2.gmarkup

@@ -0,0 +1 @@
+<EFBFBD>ν語

tests/markups/fail-20.gmarkup

@@ -0,0 +1 @@
+<foo bar=

tests/markups/fail-21.gmarkup

@@ -0,0 +1 @@
+<foo bar="fdsf

tests/markups/fail-22.gmarkup

@@ -0,0 +1 @@
+<foo>

tests/markups/fail-23.gmarkup

@@ -0,0 +1,2 @@
+<foo>
+<fo

tests/markups/fail-24.gmarkup

@@ -0,0 +1 @@
+<!-- dfklsjdf;kljsdf;ljk document ends here

tests/markups/fail-25.gmarkup

@@ -0,0 +1 @@
+<? document ending unexpectedly

tests/markups/fail-26.gmarkup

@@ -0,0 +1 @@
+<foo>&;</foo>

tests/markups/fail-27.gmarkup

@@ -0,0 +1 @@
+<foo>&|;</foo>

tests/markups/fail-28.gmarkup

@@ -0,0 +1 @@
+<foo>&am|;</foo>

tests/markups/fail-29.gmarkup

@@ -0,0 +1 @@
+<foo>&bar;</foo>

tests/markups/fail-3.gmarkup

@@ -0,0 +1,49 @@
+<foobar>
+Παν語
+
+This is a list of ways to say hello in various languages. Its purpose is to illustrate a number of scripts.
+
+(Converted into UTF-8)
+
+---------------------------------------------------------
+Arabic	السلام عليكم
+Czech	(česky)	Dobrý den
+Danish	(Dansk)	Hej, Goddag
+English	Hello
+Esperanto	Saluton
+Estonian	Tere, Tervist
+FORTRAN	PROGRAM
+Finnish	(Suomi)	Hei
+French	(Français)	Bonjour, Salut
+German	(Deutsch Nord)	Guten Tag
+German	(Deutsch Süd)	Grüß Gott
+Greek	(Ελληνικά)	Γειά σας
+Hebrew	שלום
+Hindi	नमस्ते, <20><>मस्कार।
+Italiano	Ciao, Buon giorno
+Maltese	Ċaw, Saħħa
+Nederlands, Vlaams	Hallo, Dag
+Norwegian	(Norsk)	Hei, God dag
+Polish	Dzień dobry, Hej
+Russian	(Русский)	Здравствуйте!‎
+Slovak	Dobrý deň
+Spanish	(Español)	‎¡Hola!‎
+Swedish	(Svenska)	Hej, Goddag
+Thai	(ภาษาไทย)	สวัสดีครับ, สวัสดีค่ะ
+Turkish	(Türkçe)	Merhaba
+Vietnamese	(Tiếng Việt)	Xin Chào
+Yiddish	(ײַדישע)	דאָס הײַזעלע 
+
+Japanese	(日本語)	こんにちは, ｺﾝﾆﾁﾊ
+Chinese	(中文,普通话,汉语)	你好
+Cantonese	(粵語,廣東話)	早晨, 你好
+Korean	(한글)	안녕하세요, 안녕하십니까
+
+Difference among chinese characters in GB, JIS, KSC, BIG5:‎
+ GB	--	元气	开发
+ JIS	--	元気	開発
+ KSC	--	元氣	開發
+ BIG5	--	元氣	開發
+
+
+</foobar>

tests/markups/fail-30.gmarkup

@@ -0,0 +1 @@
+<foo>&sdfkljsdsdfsdfsdfsdf</foo>

tests/markups/fail-31.gmarkup

@@ -0,0 +1 @@
+<foo>&#34592348345343453453455645765736575865767;</foo>

tests/markups/fail-32.gmarkup

@@ -0,0 +1 @@
+<foo>&#x10;</foo>

tests/markups/fail-33.gmarkup

@@ -0,0 +1 @@
+<foo>&#;</foo>

tests/markups/fail-34.gmarkup

@@ -0,0 +1 @@
+<foo>&#234234</foo>

tests/markups/fail-4.gmarkup

@@ -0,0 +1 @@
+foo

tests/markups/fail-5.gmarkup

@@ -0,0 +1,2 @@
+<|foo>
+</|foo>

tests/markups/fail-6.gmarkup

@@ -0,0 +1,2 @@
+<foo|>
+</foo>

tests/markups/fail-7.gmarkup

@@ -0,0 +1,2 @@
+<foo bar}"baz">
+</foo>

tests/markups/fail-8.gmarkup

@@ -0,0 +1,2 @@
+<foo/}>
+</foo>

tests/markups/fail-9.gmarkup

@@ -0,0 +1,2 @@
+<foo bar={baz">
+</foo>

tests/markups/valid-1.gmarkup

@@ -0,0 +1,9 @@
+  <!-- Comment -->
+<?PI ?>
+<foobar>
+<e1>Hi &amp; this is some text inside an element Two 'E' chars as character refs: &#69; &#x45; and some 'J': &#74; &#x4A;</e1>
+<e2:foo> Text <childfree/> with some <nested>nested elements</nested> and entities &quot;&amp;  &lt; &gt;&gt; &apos; and whitespace    </e2:foo>
+<tag ab="fo&lt;o" bar="foo" baz="blah">This element has attributes</tag>
+<nochildren a="b" xyz="qrs"/>
+</foobar>
+   

tests/markups/valid-2.gmarkup

@@ -0,0 +1,49 @@
+<foobar>
+Παν語
+
+This is a list of ways to say hello in various languages. Its purpose is to illustrate a number of scripts.
+
+(Converted into UTF-8)
+
+---------------------------------------------------------
+Arabic	السلام عليكم
+Czech	(česky)	Dobrý den
+Danish	(Dansk)	Hej, Goddag
+English	Hello
+Esperanto	Saluton
+Estonian	Tere, Tervist
+FORTRAN	PROGRAM
+Finnish	(Suomi)	Hei
+French	(Français)	Bonjour, Salut
+German	(Deutsch Nord)	Guten Tag
+German	(Deutsch Süd)	Grüß Gott
+Greek	(Ελληνικά)	Γειά σας
+Hebrew	שלום
+Hindi	नमस्ते, नमस्कार।
+Italiano	Ciao, Buon giorno
+Maltese	Ċaw, Saħħa
+Nederlands, Vlaams	Hallo, Dag
+Norwegian	(Norsk)	Hei, God dag
+Polish	Dzień dobry, Hej
+Russian	(Русский)	Здравствуйте!‎
+Slovak	Dobrý deň
+Spanish	(Español)	‎¡Hola!‎
+Swedish	(Svenska)	Hej, Goddag
+Thai	(ภาษาไทย)	สวัสดีครับ, สวัสดีค่ะ
+Turkish	(Türkçe)	Merhaba
+Vietnamese	(Tiếng Việt)	Xin Chào
+Yiddish	(ײַדישע)	דאָס הײַזעלע 
+
+Japanese	(日本語)	こんにちは, ｺﾝﾆﾁﾊ
+Chinese	(中文,普通话,汉语)	你好
+Cantonese	(粵語,廣東話)	早晨, 你好
+Korean	(한글)	안녕하세요, 안녕하십니까
+
+Difference among chinese characters in GB, JIS, KSC, BIG5:‎
+ GB	--	元气	开发
+ JIS	--	元気	開発
+ KSC	--	元氣	開發
+ BIG5	--	元氣	開發
+
+
+</foobar>

tests/run-markup-tests.sh

@@ -0,0 +1,19 @@
+#! /bin/sh
+
+fail ()
+{
+  echo "Test failed: $*"
+  exit 1
+}
+
+for I in markups/fail-*.gmarkup; do
+  echo "Parsing $I, should fail"
+  ./markup-test $I > /dev/null && fail "failed to generate error on $I"
+done
+
+for I in markups/valid-*.gmarkup; do
+  echo "Parsing $I, should succeed"
+  ./markup-test $I > /dev/null || fail "failed on $I"
+done
+
+echo "All tests passed."