* SECTION:gregex
* @title: Perl-compatible regular expressions
* @short_description: matches strings against regular expressions
- * @see_also: <xref linkend="glib-regex-syntax"/>
+ * @see_also: [Regular expression syntax][glib-regex-syntax]
*
- * The <function>g_regex_*()</function> functions implement regular
+ * The g_regex_*() functions implement regular
* expression pattern matching using syntax and semantics similar to
* Perl regular expression.
*
* '\U' always matches 'U' instead of being an error in the pattern. Finally,
* pattern matching is modified so that back references to an unset subpattern
* group produces a match with the empty string instead of an error. See
- * <ulink>man:pcreapi(3)</ulink> for more information.
+ * pcreapi(3) for more information.
*
* Creating and manipulating the same #GRegex structure from different
* threads is not a problem as #GRegex does not modify its internal
* is not threadsafe.
*
* The regular expressions low-level functionalities are obtained through
- * the excellent <ulink url="http://www.pcre.org/">PCRE</ulink> library
- * written by Philip Hazel.
+ * the excellent
+ * [PCRE](http://www.pcre.org/)
+ * library written by Philip Hazel.
*/
/* Mask of all the possible values for GRegexCompileFlags. */
* stops at the partial match.
* When both #G_REGEX_MATCH_PARTIAL_SOFT and #G_REGEX_MATCH_PARTIAL_HARD
* are set, the latter takes precedence.
- * See <ulink>man:pcrepartial</ulink> for more information on partial matching.
- *
- * Because of the way certain internal optimizations are implemented
- * the partial matching algorithm cannot be used with all patterns.
- * So repeated single characters such as "a{2,4}" and repeated single
- * meta-sequences such as "\d+" are not permitted if the maximum number
- * of occurrences is greater than one. Optional items such as "\d?"
- * (where the maximum is one) are permitted. Quantifiers with any values
- * are permitted after parentheses, so the invalid examples above can be
- * coded thus "(a){2,4}" and "(\d)+". If #G_REGEX_MATCH_PARTIAL or
- * #G_REGEX_MATCH_PARTIAL_HARD is set
- * for a pattern that does not conform to the restrictions, matching
- * functions return an error.
+ *
+ * There were formerly some restrictions on the pattern for partial matching.
+ * The restrictions no longer apply.
+ *
+ * See pcrepartial(3) for more information on partial matching.
*
* Returns: %TRUE if the match was partial, %FALSE otherwise
*
* @match_info: #GMatchInfo structure
* @match_num: number of the sub expression
*
- * Retrieves the text matching the @match_num<!-- -->'th capturing
+ * Retrieves the text matching the @match_num'th capturing
* parentheses. 0 is the full text of the match, 1 is the first paren
* set, 2 the second, and so on.
*
* @end_pos: (out) (allow-none): pointer to location where to store
* the end position, or %NULL
*
- * Retrieves the position in bytes of the @match_num<!-- -->'th capturing
+ * Retrieves the position in bytes of the @match_num'th capturing
* parentheses. 0 is the full text of the match, 1 is the first
* paren set, 2 the second, and so on.
*
* Retrieves the text matching the capturing parentheses named @name.
*
* If @name is a valid sub pattern name but it didn't match anything
- * (e.g. sub pattern "X", matching "b" against "(?P<X>a)?b")
+ * (e.g. sub pattern "X", matching "b" against "(?P<X>a)?b")
* then an empty string is returned.
*
* The string is fetched from the string passed to the match function,
* Retrieves the position in bytes of the capturing parentheses named @name.
*
* If @name is a valid sub pattern name but it didn't match anything
- * (e.g. sub pattern "X", matching "b" against "(?P<X>a)?b")
+ * (e.g. sub pattern "X", matching "b" against "(?P<X>a)?b")
* then @start_pos and @end_pos are set to -1 and %TRUE is returned.
*
* Returns: %TRUE if the position was fetched, %FALSE otherwise.
}
/**
+ * g_regex_get_max_lookbehind:
+ * @regex: a #GRegex structure
+ *
+ * Gets the number of characters in the longest lookbehind assertion in the
+ * pattern. This information is useful when doing multi-segment matching using
+ * the partial matching facilities.
+ *
+ * Returns: the number of characters in the longest lookbehind assertion.
+ *
+ * Since: 2.38
+ */
+gint
+g_regex_get_max_lookbehind (const GRegex *regex)
+{
+ gint max_lookbehind;
+
+ pcre_fullinfo (regex->pcre_re, regex->extra,
+ PCRE_INFO_MAXLOOKBEHIND, &max_lookbehind);
+
+ return max_lookbehind;
+}
+
+/**
* g_regex_get_compile_flags:
* @regex: a #GRegex
*
* To retrieve all the non-overlapping matches of the pattern in
* string you can use g_match_info_next().
*
- * |[
+ * |[<!-- language="C" -->
* static void
* print_uppercase_words (const gchar *string)
* {
- * /* Print all uppercase-only words. */
+ * // Print all uppercase-only words.
* GRegex *regex;
* GMatchInfo *match_info;
- *
+ *
* regex = g_regex_new ("[A-Z]+", 0, 0, NULL);
- * g_regex_match (regex, string, 0, &match_info);
+ * g_regex_match (regex, string, 0, &match_info);
* while (g_match_info_matches (match_info))
* {
* gchar *word = g_match_info_fetch (match_info, 0);
* To retrieve all the non-overlapping matches of the pattern in
* string you can use g_match_info_next().
*
- * |[
+ * |[<!-- language="C" -->
* static void
* print_uppercase_words (const gchar *string)
* {
- * /* Print all uppercase-only words. */
+ * // Print all uppercase-only words.
* GRegex *regex;
* GMatchInfo *match_info;
* GError *error = NULL;
- *
+ *
* regex = g_regex_new ("[A-Z]+", 0, 0, NULL);
- * g_regex_match_full (regex, string, -1, 0, 0, &match_info, &error);
+ * g_regex_match_full (regex, string, -1, 0, 0, &match_info, &error);
* while (g_match_info_matches (match_info))
* {
* gchar *word = g_match_info_fetch (match_info, 0);
* g_print ("Found: %s\n", word);
* g_free (word);
- * g_match_info_next (match_info, &error);
+ * g_match_info_next (match_info, &error);
* }
* g_match_info_free (match_info);
* g_regex_unref (regex);
* Using the standard algorithm for regular expression matching only
* the longest match in the string is retrieved, it is not possible
* to obtain all the available matches. For instance matching
- * "<a> <b> <c>" against the pattern "<.*>"
- * you get "<a> <b> <c>".
+ * "<a> <b> <c>" against the pattern "<.*>"
+ * you get "<a> <b> <c>".
*
* This function uses a different algorithm (called DFA, i.e. deterministic
* finite automaton), so it can retrieve all the possible matches, all
* starting at the same point in the string. For instance matching
- * "<a> <b> <c>" against the pattern "<.*>"
- * you would obtain three matches: "<a> <b> <c>",
- * "<a> <b>" and "<a>".
+ * "<a> <b> <c>" against the pattern "<.*>;"
+ * you would obtain three matches: "<a> <b> <c>",
+ * "<a> <b>" and "<a>".
*
* The number of matched strings is retrieved using
* g_match_info_get_match_count(). To obtain the matched strings and
*
* Replaces all occurrences of the pattern in @regex with the
* replacement text. Backreferences of the form '\number' or
- * '\g<number>' in the replacement text are interpolated by the
- * number-th captured subexpression of the match, '\g<name>' refers
- * to the captured subexpression with the given name. '\0' refers to the
- * complete match, but '\0' followed by a number is the octal representation
- * of a character. To include a literal '\' in the replacement, write '\\'.
+ * '\g<number>' in the replacement text are interpolated by the
+ * number-th captured subexpression of the match, '\g<name>' refers
+ * to the captured subexpression with the given name. '\0' refers
+ * to the complete match, but '\0' followed by a number is the octal
+ * representation of a character. To include a literal '\' in the
+ * replacement, write '\\'.
+ *
* There are also escapes that changes the case of the following text:
*
- * <variablelist>
- * <varlistentry><term>\l</term>
- * <listitem>
- * <para>Convert to lower case the next character</para>
- * </listitem>
- * </varlistentry>
- * <varlistentry><term>\u</term>
- * <listitem>
- * <para>Convert to upper case the next character</para>
- * </listitem>
- * </varlistentry>
- * <varlistentry><term>\L</term>
- * <listitem>
- * <para>Convert to lower case till \E</para>
- * </listitem>
- * </varlistentry>
- * <varlistentry><term>\U</term>
- * <listitem>
- * <para>Convert to upper case till \E</para>
- * </listitem>
- * </varlistentry>
- * <varlistentry><term>\E</term>
- * <listitem>
- * <para>End case modification</para>
- * </listitem>
- * </varlistentry>
- * </variablelist>
+ * - \l: Convert to lower case the next character
+ * - \u: Convert to upper case the next character
+ * - \L: Convert to lower case till \E
+ * - \U: Convert to upper case till \E
+ * - \E: End case modification
*
* If you do not need to use backreferences use g_regex_replace_literal().
*
*
* The following example uses g_regex_replace_eval() to replace multiple
* strings at once:
- * |[
+ * |[<!-- language="C" -->
* static gboolean
* eval_cb (const GMatchInfo *info,
* GString *res,
* return FALSE;
* }
*
- * /* ... */
+ * ...
*
* GRegex *reg;
* GHashTable *h;
* res = g_regex_replace_eval (reg, text, -1, 0, 0, eval_cb, h, NULL);
* g_hash_table_destroy (h);
*
- * /* ... */
+ * ...
* ]|
*
* Returns: a newly allocated string containing the replacements