/* gmarkup.c - Simple XML-like parser
*
* Copyright 2000, 2003 Red Hat, Inc.
+ * Copyright 2007, 2008 Ryan Lortie <desrt@desrt.ca>
*
* GLib is free software; you can redistribute it and/or modify it
* under the terms of the GNU Lesser General Public License as
#include <stdlib.h>
#include <errno.h>
-#include "galias.h"
#include "glib.h"
-
#include "glibintl.h"
+#include "galias.h"
GQuark
g_markup_error_quark (void)
{
- static GQuark error_quark = 0;
-
- if (error_quark == 0)
- error_quark = g_quark_from_static_string ("g-markup-error-quark");
-
- return error_quark;
+ return g_quark_from_static_string ("g-markup-error-quark");
}
typedef enum
STATE_ERROR
} GMarkupParseState;
+typedef struct
+{
+ const char *prev_element;
+ const GMarkupParser *prev_parser;
+ gpointer prev_user_data;
+} GMarkupRecursionTracker;
+
struct _GMarkupParseContext
{
const GMarkupParser *parser;
guint document_empty : 1;
guint parsing : 1;
+ guint awaiting_pop : 1;
gint balance;
+
+ /* subparser support */
+ GSList *subparser_stack; /* (GMarkupRecursionTracker *) */
+ const char *subparser_element;
+ gpointer held_user_data;
};
/**
context->document_empty = TRUE;
context->parsing = FALSE;
+ context->awaiting_pop = FALSE;
+ context->subparser_stack = NULL;
+ context->subparser_element = NULL;
+
+ /* this is only looked at if awaiting_pop = TRUE. initialise anyway. */
+ context->held_user_data = NULL;
+
context->balance = 0;
return context;
* @context: a #GMarkupParseContext
*
* Frees a #GMarkupParseContext. Can't be called from inside
- * one of the #GMarkupParser functions.
- *
+ * one of the #GMarkupParser functions. Can't be called while
+ * a subparser is pushed.
**/
void
g_markup_parse_context_free (GMarkupParseContext *context)
{
g_return_if_fail (context != NULL);
g_return_if_fail (!context->parsing);
+ g_return_if_fail (!context->subparser_stack);
+ g_return_if_fail (!context->awaiting_pop);
if (context->dnotify)
(* context->dnotify) (context->user_data);
g_free (context);
}
+static void pop_subparser_stack (GMarkupParseContext *context);
+
static void
mark_error (GMarkupParseContext *context,
GError *error)
if (context->parser->error)
(*context->parser->error) (context, error, context->user_data);
+
+ /* report the error all the way up to free all the user-data */
+ while (context->subparser_stack)
+ {
+ pop_subparser_stack (context);
+ context->awaiting_pop = FALSE; /* already been freed */
+
+ if (context->parser->error)
+ (*context->parser->error) (context, error, context->user_data);
+ }
+}
+
+static void set_error (GMarkupParseContext *context,
+ GError **error,
+ GMarkupError code,
+ const gchar *format,
+ ...) G_GNUC_PRINTF (4, 5);
+
+static void
+set_error_literal (GMarkupParseContext *context,
+ GError **error,
+ GMarkupError code,
+ const gchar *message)
+{
+ GError *tmp_error;
+
+ tmp_error = g_error_new_literal (G_MARKUP_ERROR, code, message);
+
+ g_prefix_error (&tmp_error,
+ _("Error on line %d char %d: "),
+ context->line_number,
+ context->char_number);
+
+ mark_error (context, tmp_error);
+
+ g_propagate_error (error, tmp_error);
}
static void
const gchar *format,
...)
{
- GError *tmp_error;
gchar *s;
+ gchar *s_valid;
va_list args;
va_start (args, format);
s = g_strdup_vprintf (format, args);
va_end (args);
- tmp_error = g_error_new (G_MARKUP_ERROR,
- code,
- _("Error on line %d char %d: %s"),
- context->line_number,
- context->char_number,
- s);
+ /* Make sure that the GError message is valid UTF-8 even if it is
+ * complaining about invalid UTF-8 in the markup: */
+ s_valid = _g_utf8_make_valid (s);
+ set_error_literal (context, error, code, s);
g_free (s);
+ g_free (s_valid);
+}
- mark_error (context, tmp_error);
+static void
+propagate_error (GMarkupParseContext *context,
+ GError **dest,
+ GError *src)
+{
+ if (context->flags & G_MARKUP_PREFIX_ERROR_POSITION)
+ g_prefix_error (&src,
+ _("Error on line %d char %d: "),
+ context->line_number,
+ context->char_number);
- g_propagate_error (error, tmp_error);
-}
+ mark_error (context, src);
+ g_propagate_error (dest, src);
+}
/* To make these faster, we first use the ascii-only tests, then check
* for the usual non-alnum name-end chars, and only then call the
((c) == '=' || (c) == '/' || (c) == '>' || (c) == ' ')
static gboolean
-is_name_start_char (gunichar c)
+is_name_start_char (const gchar *p)
{
- if (g_ascii_isalpha (c) ||
- (!IS_COMMON_NAME_END_CHAR (c) &&
- (g_unichar_isalpha (c) ||
- c == '_' ||
- c == ':')))
+ if (g_ascii_isalpha (*p) ||
+ (!IS_COMMON_NAME_END_CHAR (*p) &&
+ (*p == '_' ||
+ *p == ':' ||
+ g_unichar_isalpha (g_utf8_get_char (p)))))
return TRUE;
else
return FALSE;
}
static gboolean
-is_name_char (gunichar c)
+is_name_char (const gchar *p)
{
- if (g_ascii_isalnum (c) ||
- (!IS_COMMON_NAME_END_CHAR (c) &&
- (g_unichar_isalnum (c) ||
- c == '.' ||
- c == '-' ||
- c == '_' ||
- c == ':')))
+ if (g_ascii_isalnum (*p) ||
+ (!IS_COMMON_NAME_END_CHAR (*p) &&
+ (*p == '.' ||
+ *p == '-' ||
+ *p == '_' ||
+ *p == ':' ||
+ g_unichar_isalpha (g_utf8_get_char (p)))))
return TRUE;
else
return FALSE;
char_str (gunichar c,
gchar *buf)
{
- memset (buf, 0, 7);
+ memset (buf, 0, 8);
g_unichar_to_utf8 (c, buf);
return buf;
}
return p;
}
-__attribute__ ((noinline))
static const gchar*
unescape_text_state_after_ampersand (UnescapeContext *ucontext,
const gchar *p,
ucontext->entity_start = p;
ucontext->state = USTATE_AFTER_CHARREF_HASH;
}
- else if (!is_name_start_char (g_utf8_get_char (p)))
+ else if (!is_name_start_char (p))
{
if (*p == ';')
{
}
else
{
- gchar buf[7];
+ gchar buf[8];
set_unescape_error (ucontext->context, error,
p, ucontext->text_end,
return p;
}
-__attribute__ ((noinline))
static const gchar*
unescape_text_state_inside_entity_name (UnescapeContext *ucontext,
const gchar *p,
GError **error)
{
-#define MAX_ENT_LEN 5
- gchar buf[MAX_ENT_LEN+1] = {
- '\0', '\0', '\0', '\0', '\0', '\0'
- };
- gchar *dest;
-
while (p != ucontext->text_end)
{
if (*p == ';')
break;
- else if (!is_name_char (*p))
+ else if (!is_name_char (p))
{
- gchar ubuf[7];
+ gchar ubuf[8];
set_unescape_error (ucontext->context, error,
p, ucontext->text_end,
{
if (p != ucontext->text_end)
{
- const gchar *src;
-
- src = ucontext->entity_start;
- dest = buf;
- while (src != p)
- {
- *dest = *src;
- ++dest;
- ++src;
- }
+ gint len = p - ucontext->entity_start;
/* move to after semicolon */
p = g_utf8_next_char (p);
ucontext->state = USTATE_INSIDE_TEXT;
- if (strcmp (buf, "lt") == 0)
+ if (strncmp (ucontext->entity_start, "lt", len) == 0)
g_string_append_c (ucontext->str, '<');
- else if (strcmp (buf, "gt") == 0)
+ else if (strncmp (ucontext->entity_start, "gt", len) == 0)
g_string_append_c (ucontext->str, '>');
- else if (strcmp (buf, "amp") == 0)
+ else if (strncmp (ucontext->entity_start, "amp", len) == 0)
g_string_append_c (ucontext->str, '&');
- else if (strcmp (buf, "quot") == 0)
+ else if (strncmp (ucontext->entity_start, "quot", len) == 0)
g_string_append_c (ucontext->str, '"');
- else if (strcmp (buf, "apos") == 0)
+ else if (strncmp (ucontext->entity_start, "apos", len) == 0)
g_string_append_c (ucontext->str, '\'');
else
{
+ gchar *name;
+
+ name = g_strndup (ucontext->entity_start, len);
set_unescape_error (ucontext->context, error,
p, ucontext->text_end,
G_MARKUP_ERROR_PARSE,
_("Entity name '%s' is not known"),
- buf);
+ name);
+ g_free (name);
}
}
else
return p;
}
-__attribute__ ((noinline))
static const gchar*
unescape_text_state_after_charref_hash (UnescapeContext *ucontext,
const gchar *p,
if (start != p)
{
- gchar *digit = g_strndup (start, p - start);
gulong l;
gchar *end = NULL;
- gchar *digit_end = digit + (p - start);
errno = 0;
if (is_hex)
- l = strtoul (digit, &end, 16);
+ l = strtoul (start, &end, 16);
else
- l = strtoul (digit, &end, 10);
+ l = strtoul (start, &end, 10);
- if (end != digit_end || errno != 0)
+ if (end != p || errno != 0)
{
set_unescape_error (ucontext->context, error,
start, ucontext->text_end,
G_MARKUP_ERROR_PARSE,
- _("Failed to parse '%s', which "
+ _("Failed to parse '%-.*s', which "
"should have been a digit "
"inside a character reference "
"(ê for example) - perhaps "
"the digit is too large"),
- digit);
+ p - start, start);
}
else
{
- /* characters XML permits */
- if (l == 0x9 ||
- l == 0xA ||
- l == 0xD ||
- (l >= 0x20 && l <= 0xD7FF) ||
- (l >= 0xE000 && l <= 0xFFFD) ||
- (l >= 0x10000 && l <= 0x10FFFF))
+ /* characters XML 1.1 permits */
+ if ((0 < l && l <= 0xD7FF) ||
+ (0xE000 <= l && l <= 0xFFFD) ||
+ (0x10000 <= l && l <= 0x10FFFF))
{
- gchar buf[7];
+ gchar buf[8];
g_string_append (ucontext->str, char_str (l, buf));
}
else
set_unescape_error (ucontext->context, error,
start, ucontext->text_end,
G_MARKUP_ERROR_PARSE,
- _("Character reference '%s' does not encode a permitted character"),
- digit);
+ _("Character reference '%-.*s' does not "
+ "encode a permitted character"),
+ p - start, start);
}
}
- g_free (digit);
-
/* Move to next state */
p = g_utf8_next_char (p); /* past semicolon */
ucontext->state = USTATE_INSIDE_TEXT;
{
do
{
- if (!is_name_char (g_utf8_get_char (context->iter)))
+ if (!is_name_char (context->iter))
return;
}
while (advance_char (context));
return context->tag_stack->data;
}
+static void
+pop_subparser_stack (GMarkupParseContext *context)
+{
+ GMarkupRecursionTracker *tracker;
+
+ g_assert (context->subparser_stack);
+
+ tracker = context->subparser_stack->data;
+
+ context->awaiting_pop = TRUE;
+ context->held_user_data = context->user_data;
+
+ context->user_data = tracker->prev_user_data;
+ context->parser = tracker->prev_parser;
+ context->subparser_element = tracker->prev_element;
+ g_slice_free (GMarkupRecursionTracker, tracker);
+
+ context->subparser_stack = g_slist_delete_link (context->subparser_stack,
+ context->subparser_stack);
+}
+
+static void
+possibly_finish_subparser (GMarkupParseContext *context)
+{
+ if (current_element (context) == context->subparser_element)
+ pop_subparser_stack (context);
+}
+
+static void
+ensure_no_outstanding_subparser (GMarkupParseContext *context)
+{
+ if (context->awaiting_pop)
+ g_critical ("During the first end_element call after invoking a "
+ "subparser you must pop the subparser stack and handle "
+ "the freeing of the subparser user_data. This can be "
+ "done by calling the end function of the subparser. "
+ "Very probably, your program just leaked memory.");
+
+ /* let valgrind watch the pointer disappear... */
+ context->held_user_data = NULL;
+ context->awaiting_pop = FALSE;
+}
+
static const gchar*
current_attribute (GMarkupParseContext *context)
{
/* The leftover char portion is too big to be
* a UTF-8 character
*/
- set_error (context,
- error,
- G_MARKUP_ERROR_BAD_UTF8,
- _("Invalid UTF-8 encoded text"));
+ set_error_literal (context,
+ error,
+ G_MARKUP_ERROR_BAD_UTF8,
+ _("Invalid UTF-8 encoded text - overlong sequence"));
}
goto finished;
*/
if ((*context->current_text & 0xc0) == 0x80) /* not a char start */
{
- set_error (context,
- error,
- G_MARKUP_ERROR_BAD_UTF8,
- _("Invalid UTF-8 encoded text"));
+ set_error_literal (context,
+ error,
+ G_MARKUP_ERROR_BAD_UTF8,
+ _("Invalid UTF-8 encoded text - not a start char"));
goto finished;
}
&first_invalid))
{
gint newlines = 0;
- const gchar *p;
- p = context->current_text;
- while (p != context->current_text_end)
+ const gchar *p, *q;
+ gchar *current_text_dup;
+
+ q = p = context->current_text;
+ while (p != first_invalid)
{
if (*p == '\n')
- ++newlines;
+ {
+ ++newlines;
+ q = p + 1;
+ context->char_number = 1;
+ }
++p;
}
context->line_number += newlines;
+ context->char_number += g_utf8_strlen (q, first_invalid - q);
+ current_text_dup = g_strndup (context->current_text, context->current_text_len);
set_error (context,
error,
G_MARKUP_ERROR_BAD_UTF8,
- _("Invalid UTF-8 encoded text"));
+ _("Invalid UTF-8 encoded text - not valid '%s'"),
+ current_text_dup);
+ g_free (current_text_dup);
goto finished;
}
}
else
{
- set_error (context,
- error,
- G_MARKUP_ERROR_PARSE,
- _("Document must begin with an element (e.g. <book>)"));
+ set_error_literal (context,
+ error,
+ G_MARKUP_ERROR_PARSE,
+ _("Document must begin with an element (e.g. <book>)"));
}
}
break;
context->state = STATE_AFTER_CLOSE_TAG_SLASH;
}
- else if (is_name_start_char (g_utf8_get_char (context->iter)))
+ else if (is_name_start_char (context->iter))
{
context->state = STATE_INSIDE_OPEN_TAG_NAME;
}
else
{
- gchar buf[7];
+ gchar buf[8];
+
set_error (context,
error,
G_MARKUP_ERROR_PARSE,
g_assert (context->tag_stack != NULL);
+ possibly_finish_subparser (context);
+
tmp_error = NULL;
if (context->parser->end_element)
(* context->parser->end_element) (context,
context->tag_stack->data,
context->user_data,
&tmp_error);
+
+ ensure_no_outstanding_subparser (context);
if (tmp_error)
{
}
else
{
- gchar buf[7];
+ gchar buf[8];
+
set_error (context,
error,
G_MARKUP_ERROR_PARSE,
_("Odd character '%s', expected a '>' character "
- "to end the start tag of element '%s'"),
+ "to end the empty-element tag '%s'"),
utf8_str (context->iter, buf),
current_element (context));
}
}
else
{
- gchar buf[7];
+ gchar buf[8];
+
set_error (context,
error,
G_MARKUP_ERROR_PARSE,
advance_char (context);
context->state = STATE_AFTER_CLOSE_ANGLE;
}
- else if (is_name_start_char (g_utf8_get_char (context->iter)))
+ else if (is_name_start_char (context->iter))
{
context->state = STATE_INSIDE_ATTRIBUTE_NAME;
/* start of attribute name */
}
else
{
- gchar buf[7];
+ gchar buf[8];
+
set_error (context,
error,
G_MARKUP_ERROR_PARSE,
context->attr_values[0] == NULL);
if (tmp_error != NULL)
- {
- mark_error (context, tmp_error);
- g_propagate_error (error, tmp_error);
- }
+ propagate_error (context, error, tmp_error);
}
}
break;
}
else
{
- gchar buf[7];
+ gchar buf[8];
+
set_error (context,
error,
G_MARKUP_ERROR_PARSE,
context->start = context->iter;
}
else
- {
- mark_error (context, tmp_error);
- g_propagate_error (error, tmp_error);
- }
+ propagate_error (context, error, tmp_error);
}
truncate_partial (context);
case STATE_AFTER_CLOSE_TAG_SLASH:
/* Possible next state: INSIDE_CLOSE_TAG_NAME */
- if (is_name_start_char (g_utf8_get_char (context->iter)))
+ if (is_name_start_char (context->iter))
{
context->state = STATE_INSIDE_CLOSE_TAG_NAME;
}
else
{
- gchar buf[7];
+ gchar buf[8];
+
set_error (context,
error,
G_MARKUP_ERROR_PARSE,
if (*context->iter != '>')
{
- gchar buf[7];
+ gchar buf[8];
+
set_error (context,
error,
G_MARKUP_ERROR_PARSE,
context->state = STATE_AFTER_CLOSE_ANGLE;
context->start = NULL;
+ possibly_finish_subparser (context);
+
/* call the end_element callback */
tmp_error = NULL;
if (context->parser->end_element)
context->user_data,
&tmp_error);
+ ensure_no_outstanding_subparser (context);
/* Pop the tag stack */
g_free (context->tag_stack->data);
context->tag_stack);
if (tmp_error)
- {
- mark_error (context, tmp_error);
- g_propagate_error (error, tmp_error);
- }
+ propagate_error (context, error, tmp_error);
}
g_free (close_name);
if (*context->iter == '<')
context->balance++;
if (*context->iter == '>')
- {
+ {
+ gchar *str;
+ gsize len;
+
context->balance--;
add_to_partial (context, context->start, context->iter);
context->start = context->iter;
- if ((g_str_has_prefix (context->partial_chunk->str, "<?")
- && g_str_has_suffix (context->partial_chunk->str, "?")) ||
- (g_str_has_prefix (context->partial_chunk->str, "<!--")
- && g_str_has_suffix (context->partial_chunk->str, "--")) ||
- (g_str_has_prefix (context->partial_chunk->str, "<![CDATA[")
- && g_str_has_suffix (context->partial_chunk->str, "]]")) ||
- (g_str_has_prefix (context->partial_chunk->str, "<!DOCTYPE")
- && context->balance == 0))
+
+ str = context->partial_chunk->str;
+ len = context->partial_chunk->len;
+
+ if (str[1] == '?' && str[len - 1] == '?')
+ break;
+ if (strncmp (str, "<!--", 4) == 0 &&
+ strcmp (str + len - 2, "--") == 0)
+ break;
+ if (strncmp (str, "<![CDATA[", 9) == 0 &&
+ strcmp (str + len - 2, "]]") == 0)
+ break;
+ if (strncmp (str, "<!DOCTYPE", 9) == 0 &&
+ context->balance == 0)
break;
}
}
/* The passthrough hasn't necessarily ended. Merge with
* partial chunk, leave state unchanged.
*/
- add_to_partial (context, context->start, context->iter);
+ add_to_partial (context, context->start, context->iter);
}
else
{
advance_char (context); /* advance past close angle */
add_to_partial (context, context->start, context->iter);
- if (context->parser->passthrough)
+ if (context->flags & G_MARKUP_TREAT_CDATA_AS_TEXT &&
+ strncmp (context->partial_chunk->str, "<![CDATA[", 9) == 0)
+ {
+ if (context->parser->text)
+ (*context->parser->text) (context,
+ context->partial_chunk->str + 9,
+ context->partial_chunk->len - 12,
+ context->user_data,
+ &tmp_error);
+ }
+ else if (context->parser->passthrough)
(*context->parser->passthrough) (context,
context->partial_chunk->str,
context->partial_chunk->len,
context->start = context->iter; /* could begin text */
}
else
- {
- mark_error (context, tmp_error);
- g_propagate_error (error, tmp_error);
- }
+ propagate_error (context, error, tmp_error);
}
break;
if (context->document_empty)
{
- set_error (context, error, G_MARKUP_ERROR_EMPTY,
- _("Document was empty or contained only whitespace"));
+ set_error_literal (context, error, G_MARKUP_ERROR_EMPTY,
+ _("Document was empty or contained only whitespace"));
return FALSE;
}
break;
case STATE_AFTER_OPEN_ANGLE:
- set_error (context, error, G_MARKUP_ERROR_PARSE,
- _("Document ended unexpectedly just after an open angle bracket '<'"));
+ set_error_literal (context, error, G_MARKUP_ERROR_PARSE,
+ _("Document ended unexpectedly just after an open angle bracket '<'"));
break;
case STATE_AFTER_CLOSE_ANGLE:
break;
case STATE_INSIDE_OPEN_TAG_NAME:
- set_error (context, error, G_MARKUP_ERROR_PARSE,
- _("Document ended unexpectedly inside an element name"));
+ set_error_literal (context, error, G_MARKUP_ERROR_PARSE,
+ _("Document ended unexpectedly inside an element name"));
break;
case STATE_INSIDE_ATTRIBUTE_NAME:
- set_error (context, error, G_MARKUP_ERROR_PARSE,
- _("Document ended unexpectedly inside an attribute name"));
+ case STATE_AFTER_ATTRIBUTE_NAME:
+ set_error_literal (context, error, G_MARKUP_ERROR_PARSE,
+ _("Document ended unexpectedly inside an attribute name"));
break;
case STATE_BETWEEN_ATTRIBUTES:
- set_error (context, error, G_MARKUP_ERROR_PARSE,
- _("Document ended unexpectedly inside an element-opening "
- "tag."));
+ set_error_literal (context, error, G_MARKUP_ERROR_PARSE,
+ _("Document ended unexpectedly inside an element-opening "
+ "tag."));
break;
case STATE_AFTER_ATTRIBUTE_EQUALS_SIGN:
- set_error (context, error, G_MARKUP_ERROR_PARSE,
- _("Document ended unexpectedly after the equals sign "
- "following an attribute name; no attribute value"));
+ set_error_literal (context, error, G_MARKUP_ERROR_PARSE,
+ _("Document ended unexpectedly after the equals sign "
+ "following an attribute name; no attribute value"));
break;
case STATE_INSIDE_ATTRIBUTE_VALUE_SQ:
case STATE_INSIDE_ATTRIBUTE_VALUE_DQ:
- set_error (context, error, G_MARKUP_ERROR_PARSE,
- _("Document ended unexpectedly while inside an attribute "
- "value"));
+ set_error_literal (context, error, G_MARKUP_ERROR_PARSE,
+ _("Document ended unexpectedly while inside an attribute "
+ "value"));
break;
case STATE_INSIDE_TEXT:
case STATE_AFTER_CLOSE_TAG_SLASH:
case STATE_INSIDE_CLOSE_TAG_NAME:
+ case STATE_AFTER_CLOSE_TAG_NAME:
set_error (context, error, G_MARKUP_ERROR_PARSE,
_("Document ended unexpectedly inside the close tag for "
- "element '%s'"), current_element);
+ "element '%s'"), current_element (context));
break;
case STATE_INSIDE_PASSTHROUGH:
- set_error (context, error, G_MARKUP_ERROR_PARSE,
- _("Document ended unexpectedly inside a comment or "
- "processing instruction"));
+ set_error_literal (context, error, G_MARKUP_ERROR_PARSE,
+ _("Document ended unexpectedly inside a comment or "
+ "processing instruction"));
break;
case STATE_ERROR:
*
* Retrieves the name of the currently open element.
*
+ * If called from the start_element or end_element handlers this will
+ * give the element_name as passed to those functions. For the parent
+ * elements, see g_markup_parse_context_get_element_stack().
+ *
* Since: 2.2
**/
G_CONST_RETURN gchar *
}
/**
+ * g_markup_parse_context_get_element_stack:
+ * @context: a #GMarkupParseContext
+ *
+ * Retrieves the element stack from the internal state of the parser.
+ * The returned #GSList is a list of strings where the first item is
+ * the currently open tag (as would be returned by
+ * g_markup_parse_context_get_element()) and the next item is its
+ * immediate parent.
+ *
+ * This function is intended to be used in the start_element and
+ * end_element handlers where g_markup_parse_context_get_element()
+ * would merely return the name of the element that is being
+ * processed.
+ *
+ * Returns: the element stack, which must not be modified
+ *
+ * Since: 2.16
+ **/
+G_CONST_RETURN GSList *
+g_markup_parse_context_get_element_stack (GMarkupParseContext *context)
+{
+ g_return_val_if_fail (context != NULL, NULL);
+
+ return context->tag_stack;
+}
+
+/**
* g_markup_parse_context_get_position:
* @context: a #GMarkupParseContext
* @line_number: return location for a line number, or %NULL
*char_number = context->char_number;
}
+/**
+ * g_markup_parse_context_get_user_data:
+ * @context: a #GMarkupParseContext
+ *
+ * Returns the user_data associated with @context. This will either
+ * be the user_data that was provided to g_markup_parse_context_new()
+ * or to the most recent call of g_markup_parse_context_push().
+ *
+ * Returns: the provided user_data. The returned data belongs to
+ * the markup context and will be freed when g_markup_context_free()
+ * is called.
+ *
+ * Since: 2.18
+ **/
+gpointer
+g_markup_parse_context_get_user_data (GMarkupParseContext *context)
+{
+ return context->user_data;
+}
+
+/**
+ * g_markup_parse_context_push:
+ * @context: a #GMarkupParseContext
+ * @parser: a #GMarkupParser
+ * @user_data: user data to pass to #GMarkupParser functions
+ *
+ * Temporarily redirects markup data to a sub-parser.
+ *
+ * This function may only be called from the start_element handler of
+ * a #GMarkupParser. It must be matched with a corresponding call to
+ * g_markup_parse_context_pop() in the matching end_element handler
+ * (except in the case that the parser aborts due to an error).
+ *
+ * All tags, text and other data between the matching tags is
+ * redirected to the subparser given by @parser. @user_data is used
+ * as the user_data for that parser. @user_data is also passed to the
+ * error callback in the event that an error occurs. This includes
+ * errors that occur in subparsers of the subparser.
+ *
+ * The end tag matching the start tag for which this call was made is
+ * handled by the previous parser (which is given its own user_data)
+ * which is why g_markup_parse_context_pop() is provided to allow "one
+ * last access" to the @user_data provided to this function. In the
+ * case of error, the @user_data provided here is passed directly to
+ * the error callback of the subparser and g_markup_parse_context()
+ * should not be called. In either case, if @user_data was allocated
+ * then it ought to be freed from both of these locations.
+ *
+ * This function is not intended to be directly called by users
+ * interested in invoking subparsers. Instead, it is intended to be
+ * used by the subparsers themselves to implement a higher-level
+ * interface.
+ *
+ * As an example, see the following implementation of a simple
+ * parser that counts the number of tags encountered.
+ *
+ * |[
+ * typedef struct
+ * {
+ * gint tag_count;
+ * } CounterData;
+ *
+ * static void
+ * counter_start_element (GMarkupParseContext *context,
+ * const gchar *element_name,
+ * const gchar **attribute_names,
+ * const gchar **attribute_values,
+ * gpointer user_data,
+ * GError **error)
+ * {
+ * CounterData *data = user_data;
+ *
+ * data->tag_count++;
+ * }
+ *
+ * static void
+ * counter_error (GMarkupParseContext *context,
+ * GError *error,
+ * gpointer user_data)
+ * {
+ * CounterData *data = user_data;
+ *
+ * g_slice_free (CounterData, data);
+ * }
+ *
+ * static GMarkupParser counter_subparser =
+ * {
+ * counter_start_element,
+ * NULL,
+ * NULL,
+ * NULL,
+ * counter_error
+ * };
+ * ]|
+ *
+ * In order to allow this parser to be easily used as a subparser, the
+ * following interface is provided:
+ *
+ * |[
+ * void
+ * start_counting (GMarkupParseContext *context)
+ * {
+ * CounterData *data = g_slice_new (CounterData);
+ *
+ * data->tag_count = 0;
+ * g_markup_parse_context_push (context, &counter_subparser, data);
+ * }
+ *
+ * gint
+ * end_counting (GMarkupParseContext *context)
+ * {
+ * CounterData *data = g_markup_parse_context_pop (context);
+ * int result;
+ *
+ * result = data->tag_count;
+ * g_slice_free (CounterData, data);
+ *
+ * return result;
+ * }
+ * ]|
+ *
+ * The subparser would then be used as follows:
+ *
+ * |[
+ * static void start_element (context, element_name, ...)
+ * {
+ * if (strcmp (element_name, "count-these") == 0)
+ * start_counting (context);
+ *
+ * /* else, handle other tags... */
+ * }
+ *
+ * static void end_element (context, element_name, ...)
+ * {
+ * if (strcmp (element_name, "count-these") == 0)
+ * g_print ("Counted %d tags\n", end_counting (context));
+ *
+ * /* else, handle other tags... */
+ * }
+ * ]|
+ *
+ * Since: 2.18
+ **/
+void
+g_markup_parse_context_push (GMarkupParseContext *context,
+ GMarkupParser *parser,
+ gpointer user_data)
+{
+ GMarkupRecursionTracker *tracker;
+
+ tracker = g_slice_new (GMarkupRecursionTracker);
+ tracker->prev_element = context->subparser_element;
+ tracker->prev_parser = context->parser;
+ tracker->prev_user_data = context->user_data;
+
+ context->subparser_element = current_element (context);
+ context->parser = parser;
+ context->user_data = user_data;
+
+ context->subparser_stack = g_slist_prepend (context->subparser_stack,
+ tracker);
+}
+
+/**
+ * g_markup_parse_context_pop:
+ * @context: a #GMarkupParseContext
+ *
+ * Completes the process of a temporary sub-parser redirection.
+ *
+ * This function exists to collect the user_data allocated by a
+ * matching call to g_markup_parse_context_push(). It must be called
+ * in the end_element handler corresponding to the start_element
+ * handler during which g_markup_parse_context_push() was called. You
+ * must not call this function from the error callback -- the
+ * @user_data is provided directly to the callback in that case.
+ *
+ * This function is not intended to be directly called by users
+ * interested in invoking subparsers. Instead, it is intended to be
+ * used by the subparsers themselves to implement a higher-level
+ * interface.
+ *
+ * Returns: the user_data passed to g_markup_parse_context_push().
+ *
+ * Since: 2.18
+ **/
+gpointer
+g_markup_parse_context_pop (GMarkupParseContext *context)
+{
+ gpointer user_data;
+
+ if (!context->awaiting_pop)
+ possibly_finish_subparser (context);
+
+ g_assert (context->awaiting_pop);
+
+ context->awaiting_pop = FALSE;
+
+ /* valgrind friendliness */
+ user_data = context->held_user_data;
+ context->held_user_data = NULL;
+
+ return user_data;
+}
+
static void
append_escaped_text (GString *str,
const gchar *text,
{
const gchar *p;
const gchar *end;
+ gunichar c;
p = text;
end = text + length;
break;
default:
- g_string_append_len (str, p, next - p);
+ c = g_utf8_get_char (p);
+ if ((0x1 <= c && c <= 0x8) ||
+ (0xb <= c && c <= 0xc) ||
+ (0xe <= c && c <= 0x1f) ||
+ (0x7f <= c && c <= 0x84) ||
+ (0x86 <= c && c <= 0x9f))
+ g_string_append_printf (str, "&#x%x;", c);
+ else
+ g_string_append_len (str, p, next - p);
break;
}
/**
* g_markup_escape_text:
* @text: some valid UTF-8 text
- * @length: length of @text in bytes
+ * @length: length of @text in bytes, or -1 if the text is nul-terminated
*
* Escapes text so that the markup parser will parse it verbatim.
* Less than, greater than, ampersand, etc. are replaced with the
* Note that this function doesn't protect whitespace and line endings
* from being processed according to the XML rules for normalization
* of line endings and attribute values.
+ *
+ * Note also that if given a string containing them, this function
+ * will produce character references in the range of &#x1; ..
+ * &#x1f; for all control sequences except for tabstop, newline
+ * and carriage return. The character references in this range are
+ * not valid XML 1.0, but they are valid XML 1.1 and will be accepted
+ * by the GMarkup parser.
*
- * Return value: escaped text
+ * Return value: a newly allocated string with the escaped text
**/
gchar*
g_markup_escape_text (const gchar *text,
G_VA_COPY (args2, args);
output1 = g_strdup_vprintf (format1->str, args);
- va_end (args);
if (!output1)
- goto cleanup;
+ {
+ va_end (args2);
+ goto cleanup;
+ }
output2 = g_strdup_vprintf (format2->str, args2);
va_end (args2);
* output, without having to worry that the strings
* might themselves contain markup.
*
- * <informalexample><programlisting>
+ * |[
* const char *store = "Fortnum & Mason";
* const char *item = "Tea";
* char *output;
* "<item>%s</item>"
* "</purchase>",
* store, item);
- * </programlisting></informalexample>
+ * ]|
*
* Return value: newly allocated result from formatting
* operation. Free with g_free().
return result;
}
+
+static gboolean
+g_markup_parse_boolean (const char *string,
+ gboolean *value)
+{
+ char const * const falses[] = { "false", "f", "no", "n", "0" };
+ char const * const trues[] = { "true", "t", "yes", "y", "1" };
+ int i;
+
+ for (i = 0; i < G_N_ELEMENTS (falses); i++)
+ {
+ if (g_ascii_strcasecmp (string, falses[i]) == 0)
+ {
+ if (value != NULL)
+ *value = FALSE;
+
+ return TRUE;
+ }
+ }
+
+ for (i = 0; i < G_N_ELEMENTS (trues); i++)
+ {
+ if (g_ascii_strcasecmp (string, trues[i]) == 0)
+ {
+ if (value != NULL)
+ *value = TRUE;
+
+ return TRUE;
+ }
+ }
+
+ return FALSE;
+}
+
+/**
+ * GMarkupCollectType:
+ * @G_MARKUP_COLLECT_INVALID: used to terminate the list of attributes
+ * to collect.
+ * @G_MARKUP_COLLECT_STRING: collect the string pointer directly from
+ * the attribute_values[] array. Expects a
+ * parameter of type (const char **). If
+ * %G_MARKUP_COLLECT_OPTIONAL is specified
+ * and the attribute isn't present then the
+ * pointer will be set to %NULL.
+ * @G_MARKUP_COLLECT_STRDUP: as with %G_MARKUP_COLLECT_STRING, but
+ * expects a paramter of type (char **) and
+ * g_strdup()s the returned pointer. The
+ * pointer must be freed with g_free().
+ * @G_MARKUP_COLLECT_BOOLEAN: expects a parameter of type (gboolean *)
+ * and parses the attribute value as a
+ * boolean. Sets %FALSE if the attribute
+ * isn't present. Valid boolean values
+ * consist of (case insensitive) "false",
+ * "f", "no", "n", "0" and "true", "t",
+ * "yes", "y", "1".
+ * @G_MARKUP_COLLECT_TRISTATE: as with %G_MARKUP_COLLECT_BOOLEAN, but
+ * in the case of a missing attribute a
+ * value is set that compares equal to
+ * neither %FALSE nor %TRUE.
+ * G_MARKUP_COLLECT_OPTIONAL is implied.
+ * @G_MARKUP_COLLECT_OPTIONAL: can be bitwise ORed with the other
+ * fields. If present, allows the
+ * attribute not to appear. A default
+ * value is set depending on what value
+ * type is used.
+ *
+ * A mixed enumerated type and flags field. You must specify one type
+ * (string, strdup, boolean, tristate). Additionally, you may
+ * optionally bitwise OR the type with the flag
+ * %G_MARKUP_COLLECT_OPTIONAL.
+ *
+ * It is likely that this enum will be extended in the future to
+ * support other types.
+ **/
+
+/**
+ * g_markup_collect_attributes:
+ * @element_name: the current tag name
+ * @attribute_names: the attribute names
+ * @attribute_values: the attribute values
+ * @error: a pointer to a #GError or %NULL
+ * @first_type: the #GMarkupCollectType of the
+ * first attribute
+ * @first_attr: the name of the first attribute
+ * @...: a pointer to the storage location of the
+ * first attribute (or %NULL), followed by
+ * more types names and pointers, ending
+ * with %G_MARKUP_COLLECT_INVALID.
+ *
+ * Collects the attributes of the element from the
+ * data passed to the #GMarkupParser start_element
+ * function, dealing with common error conditions
+ * and supporting boolean values.
+ *
+ * This utility function is not required to write
+ * a parser but can save a lot of typing.
+ *
+ * The @element_name, @attribute_names,
+ * @attribute_values and @error parameters passed
+ * to the start_element callback should be passed
+ * unmodified to this function.
+ *
+ * Following these arguments is a list of
+ * "supported" attributes to collect. It is an
+ * error to specify multiple attributes with the
+ * same name. If any attribute not in the list
+ * appears in the @attribute_names array then an
+ * unknown attribute error will result.
+ *
+ * The #GMarkupCollectType field allows specifying
+ * the type of collection to perform and if a
+ * given attribute must appear or is optional.
+ *
+ * The attribute name is simply the name of the
+ * attribute to collect.
+ *
+ * The pointer should be of the appropriate type
+ * (see the descriptions under
+ * #GMarkupCollectType) and may be %NULL in case a
+ * particular attribute is to be allowed but
+ * ignored.
+ *
+ * This function deals with issuing errors for missing attributes
+ * (of type %G_MARKUP_ERROR_MISSING_ATTRIBUTE), unknown attributes
+ * (of type %G_MARKUP_ERROR_UNKNOWN_ATTRIBUTE) and duplicate
+ * attributes (of type %G_MARKUP_ERROR_INVALID_CONTENT) as well
+ * as parse errors for boolean-valued attributes (again of type
+ * %G_MARKUP_ERROR_INVALID_CONTENT). In all of these cases %FALSE
+ * will be returned and @error will be set as appropriate.
+ *
+ * Return value: %TRUE if successful
+ *
+ * Since: 2.16
+ **/
+gboolean
+g_markup_collect_attributes (const gchar *element_name,
+ const gchar **attribute_names,
+ const gchar **attribute_values,
+ GError **error,
+ GMarkupCollectType first_type,
+ const gchar *first_attr,
+ ...)
+{
+ GMarkupCollectType type;
+ const gchar *attr;
+ guint64 collected;
+ int written;
+ va_list ap;
+ int i;
+
+ type = first_type;
+ attr = first_attr;
+ collected = 0;
+ written = 0;
+
+ va_start (ap, first_attr);
+ while (type != G_MARKUP_COLLECT_INVALID)
+ {
+ gboolean mandatory;
+ const gchar *value;
+
+ mandatory = !(type & G_MARKUP_COLLECT_OPTIONAL);
+ type &= (G_MARKUP_COLLECT_OPTIONAL - 1);
+
+ /* tristate records a value != TRUE and != FALSE
+ * for the case where the attribute is missing
+ */
+ if (type == G_MARKUP_COLLECT_TRISTATE)
+ mandatory = FALSE;
+
+ for (i = 0; attribute_names[i]; i++)
+ if (i >= 40 || !(collected & (G_GUINT64_CONSTANT(1) << i)))
+ if (!strcmp (attribute_names[i], attr))
+ break;
+
+ /* ISO C99 only promises that the user can pass up to 127 arguments.
+ * Subtracting the first 4 arguments plus the final NULL and dividing
+ * by 3 arguments per collected attribute, we are left with a maximum
+ * number of supported attributes of (127 - 5) / 3 = 40.
+ *
+ * In reality, nobody is ever going to call us with anywhere close to
+ * 40 attributes to collect, so it is safe to assume that if i > 40
+ * then the user has given some invalid or repeated arguments. These
+ * problems will be caught and reported at the end of the function.
+ *
+ * We know at this point that we have an error, but we don't know
+ * what error it is, so just continue...
+ */
+ if (i < 40)
+ collected |= (G_GUINT64_CONSTANT(1) << i);
+
+ value = attribute_values[i];
+
+ if (value == NULL && mandatory)
+ {
+ g_set_error (error, G_MARKUP_ERROR,
+ G_MARKUP_ERROR_MISSING_ATTRIBUTE,
+ "element '%s' requires attribute '%s'",
+ element_name, attr);
+
+ va_end (ap);
+ goto failure;
+ }
+
+ switch (type)
+ {
+ case G_MARKUP_COLLECT_STRING:
+ {
+ const char **str_ptr;
+
+ str_ptr = va_arg (ap, const char **);
+
+ if (str_ptr != NULL)
+ *str_ptr = value;
+ }
+ break;
+
+ case G_MARKUP_COLLECT_STRDUP:
+ {
+ char **str_ptr;
+
+ str_ptr = va_arg (ap, char **);
+
+ if (str_ptr != NULL)
+ *str_ptr = g_strdup (value);
+ }
+ break;
+
+ case G_MARKUP_COLLECT_BOOLEAN:
+ case G_MARKUP_COLLECT_TRISTATE:
+ if (value == NULL)
+ {
+ gboolean *bool_ptr;
+
+ bool_ptr = va_arg (ap, gboolean *);
+
+ if (bool_ptr != NULL)
+ {
+ if (type == G_MARKUP_COLLECT_TRISTATE)
+ /* constructivists rejoice!
+ * neither false nor true...
+ */
+ *bool_ptr = -1;
+
+ else /* G_MARKUP_COLLECT_BOOLEAN */
+ *bool_ptr = FALSE;
+ }
+ }
+ else
+ {
+ if (!g_markup_parse_boolean (value, va_arg (ap, gboolean *)))
+ {
+ g_set_error (error, G_MARKUP_ERROR,
+ G_MARKUP_ERROR_INVALID_CONTENT,
+ "element '%s', attribute '%s', value '%s' "
+ "cannot be parsed as a boolean value",
+ element_name, attr, value);
+
+ va_end (ap);
+ goto failure;
+ }
+ }
+
+ break;
+
+ default:
+ g_assert_not_reached ();
+ }
+
+ type = va_arg (ap, GMarkupCollectType);
+ attr = va_arg (ap, const char *);
+ written++;
+ }
+ va_end (ap);
+
+ /* ensure we collected all the arguments */
+ for (i = 0; attribute_names[i]; i++)
+ if ((collected & (G_GUINT64_CONSTANT(1) << i)) == 0)
+ {
+ /* attribute not collected: could be caused by two things.
+ *
+ * 1) it doesn't exist in our list of attributes
+ * 2) it existed but was matched by a duplicate attribute earlier
+ *
+ * find out.
+ */
+ int j;
+
+ for (j = 0; j < i; j++)
+ if (strcmp (attribute_names[i], attribute_names[j]) == 0)
+ /* duplicate! */
+ break;
+
+ /* j is now the first occurance of attribute_names[i] */
+ if (i == j)
+ g_set_error (error, G_MARKUP_ERROR,
+ G_MARKUP_ERROR_UNKNOWN_ATTRIBUTE,
+ "attribute '%s' invalid for element '%s'",
+ attribute_names[i], element_name);
+ else
+ g_set_error (error, G_MARKUP_ERROR,
+ G_MARKUP_ERROR_INVALID_CONTENT,
+ "attribute '%s' given multiple times for element '%s'",
+ attribute_names[i], element_name);
+
+ goto failure;
+ }
+
+ return TRUE;
+
+failure:
+ /* replay the above to free allocations */
+ type = first_type;
+ attr = first_attr;
+
+ va_start (ap, first_attr);
+ while (type != G_MARKUP_COLLECT_INVALID)
+ {
+ gpointer ptr;
+
+ ptr = va_arg (ap, gpointer);
+
+ if (ptr == NULL)
+ continue;
+
+ switch (type & (G_MARKUP_COLLECT_OPTIONAL - 1))
+ {
+ case G_MARKUP_COLLECT_STRDUP:
+ if (written)
+ g_free (*(char **) ptr);
+
+ case G_MARKUP_COLLECT_STRING:
+ *(char **) ptr = NULL;
+ break;
+
+ case G_MARKUP_COLLECT_BOOLEAN:
+ *(gboolean *) ptr = FALSE;
+ break;
+
+ case G_MARKUP_COLLECT_TRISTATE:
+ *(gboolean *) ptr = -1;
+ break;
+ }
+
+ type = va_arg (ap, GMarkupCollectType);
+ attr = va_arg (ap, const char *);
+
+ if (written)
+ written--;
+ }
+ va_end (ap);
+
+ return FALSE;
+}
+
+#define __G_MARKUP_C__
+#include "galiasdef.c"