Use a 32-bit unsigned integer instead of a structure of 4 characters.
Add -lf_utf to dependencies on updated level projects.
Be more thorough when implementing simple fl_seek_* functions.
Support both processing char as well as f_utf_character in string processing.
Continue updating code documentation.
*
* Provides string processing functionality for what is to be defined as a serialized string.
* Serialized strings are strings that can hold multiple values in a single variable.
- * An example of serialized content is the PATH environment variable where ":" separates data..
+ * An example of serialized content is the PATH environment variable where ":" separates data.
*/
#ifndef _F_serialized_h
#define _F_serialized_h
#endif // _di_f_serialized_splitters_
#ifndef _di_f_serialized_default_allocation_step_
- #define f_serialized_default_allocation_step f_memory_default_allocation_step
+ // provide a UTF-8 friendly allocation step.
+ #define f_serialized_default_allocation_step 4
#endif // _di_f_serialized_default_allocation_step_
#ifdef __cplusplus
extern "C" {
#endif
-#ifndef _di_f_utf_is_bom_string_
- f_return_status f_utf_is_bom_string(const f_string character, const f_u_short max_width) {
+#ifndef _di_f_utf_is_bom_
+ f_return_status f_utf_is_bom(const f_string character, const f_u_short max_width) {
#ifndef _di_level_0_parameter_checking_
if (max_width < 1) return f_error_set_error(f_invalid_parameter);
#endif // _di_level_0_parameter_checking_
return f_false;
}
-#endif // _di_f_utf_is_bom_string_
+#endif // _di_f_utf_is_bom_
-#ifndef _di_f_utf_is_graph_string_
- f_return_status f_utf_is_graph_string(const f_string character, const f_u_short max_width) {
+#ifndef _di_f_utf_is_graph_
+ f_return_status f_utf_is_graph(const f_string character, const f_u_short max_width) {
#ifndef _di_level_0_parameter_checking_
if (max_width < 1) return f_error_set_error(f_invalid_parameter);
#endif // _di_level_0_parameter_checking_
// for now, just assume that any non-whitespace, non-substitute utf-8 character is a graph.
- if (f_utf_is_space_string(character, max_width) == f_true) {
+ if (f_utf_is_space(character, max_width) == f_true) {
return f_false;
}
- if (f_utf_is_bom_string(character, max_width) == f_true) {
+ if (f_utf_is_bom(character, max_width) == f_true) {
return f_false;
}
return f_true;
}
-#endif // _di_f_utf_is_graph_string_
+#endif // _di_f_utf_is_graph_
-#ifndef _di_f_utf_is_space_string_
- f_return_status f_utf_is_space_string(const f_string character, const f_u_short max_width) {
+#ifndef _di_f_utf_is_space_
+ f_return_status f_utf_is_space(const f_string character, const f_u_short max_width) {
#ifndef _di_level_0_parameter_checking_
if (max_width < 1) return f_error_set_error(f_invalid_parameter);
#endif // _di_level_0_parameter_checking_
return f_false;
}
-#endif // _di_f_utf_is_space_string_
+#endif // _di_f_utf_is_space_
-#ifndef _di_f_utf_is_substitute_string_
- f_return_status f_utf_is_substitute_string(const f_string character, const f_u_short max_width) {
+#ifndef _di_f_utf_is_substitute_
+ f_return_status f_utf_is_substitute(const f_string character, const f_u_short max_width) {
#ifndef _di_level_0_parameter_checking_
if (max_width < 1) return f_error_set_error(f_invalid_parameter);
#endif // _di_level_0_parameter_checking_
return f_false;
}
-#endif // _di_f_utf_is_substitute_string_
+#endif // _di_f_utf_is_substitute_
-#ifndef _di_f_utf_is_whitespace_string_
- f_return_status f_utf_is_whitespace_string(const f_string character, const f_u_short max_width) {
+#ifndef _di_f_utf_is_whitespace_
+ f_return_status f_utf_is_whitespace(const f_string character, const f_u_short max_width) {
#ifndef _di_level_0_parameter_checking_
if (max_width < 1) return f_error_set_error(f_invalid_parameter);
#endif // _di_level_0_parameter_checking_
return f_false;
}
-#endif // _di_f_utf_is_whitespace_string_
+#endif // _di_f_utf_is_whitespace_
#ifndef _di_f_utf_is_bom_character_
f_return_status f_utf_is_bom_character(const f_utf_character character) {
- f_u_short width = f_macro_utf_byte_width(character.byte_1);
-
- if (width == 1) {
- return f_false;
- }
-
- if (width == 3) {
- if (character.byte_1 == f_utf_bom[0] && character.byte_2 == f_utf_bom[1] && character.byte_3 == f_utf_bom[2]) {
- return f_true;
- }
+ if (character == f_macro_utf_character_mask_bom) {
+ return f_true;
}
return f_false;
#ifndef _di_f_utf_is_graph_character_
f_return_status f_utf_is_graph_character(const f_utf_character character) {
- f_u_short width = f_macro_utf_byte_width(character.byte_1);
+ f_u_short width = f_macro_utf_character_width_is(character);
if (width == 0) {
return f_false;
#ifndef _di_f_utf_is_space_character_
f_return_status f_utf_is_space_character(const f_utf_character character) {
- f_u_short width = f_macro_utf_byte_width(character.byte_1);
+ f_u_short width = f_macro_utf_character_width(character);
if (width == 1) {
return f_false;
}
if (width == 2) {
- if (character.byte_1 == f_utf_space_no_break[0] && character.byte_2 == f_utf_space_no_break[1]) {
+ char utf[2] = { f_macro_utf_character_to_char_1(character), f_macro_utf_character_to_char_2(character) };
+
+ if (utf[0] == f_utf_space_no_break[0] && utf[1] == f_utf_space_no_break[1]) {
return f_true;
}
- if (character.byte_1 == f_utf_space_line_feed_reverse[0] && character.byte_2 == f_utf_space_line_feed_reverse[1]) {
+ if (utf[0] == f_utf_space_line_feed_reverse[0] && utf[1] == f_utf_space_line_feed_reverse[1]) {
return f_true;
}
- if (character.byte_1 == f_utf_space_line_next[0] && character.byte_2 == f_utf_space_line_next[1]) {
+ if (utf[0] == f_utf_space_line_next[0] && utf[1] == f_utf_space_line_next[1]) {
return f_true;
}
- if (character.byte_1 == f_utf_substitute_middle_dot[0] && character.byte_2 == f_utf_substitute_middle_dot[1]) {
+ if (utf[0] == f_utf_substitute_middle_dot[0] && utf[1] == f_utf_substitute_middle_dot[1]) {
return f_true;
}
}
if (width == 3) {
- if (character.byte_1 == f_utf_space_no_break_narrow[0] && character.byte_2 == f_utf_space_no_break_narrow[1] && character.byte_3 == f_utf_space_no_break_narrow[2]) {
+ char utf[3] = { f_macro_utf_character_to_char_1(character), f_macro_utf_character_to_char_2(character), f_macro_utf_character_to_char_3(character) };
+
+ if (utf[0] == f_utf_space_no_break_narrow[0] && utf[1] == f_utf_space_no_break_narrow[1] && utf[2] == f_utf_space_no_break_narrow[2]) {
return f_true;
}
- if (character.byte_1 == f_utf_space_en[0] && character.byte_2 == f_utf_space_en[1] && character.byte_3 == f_utf_space_en[2]) {
+ if (utf[0] == f_utf_space_en[0] && utf[1] == f_utf_space_en[1] && utf[2] == f_utf_space_en[2]) {
return f_true;
}
- if (character.byte_1 == f_utf_space_en_quad[0] && character.byte_2 == f_utf_space_en_quad[1] && character.byte_3 == f_utf_space_en_quad[2]) {
+ if (utf[0] == f_utf_space_en_quad[0] && utf[1] == f_utf_space_en_quad[1] && utf[2] == f_utf_space_en_quad[2]) {
return f_true;
}
- if (character.byte_1 == f_utf_space_en_quad[0] && character.byte_2 == f_utf_space_en_quad[1] && character.byte_3 == f_utf_space_en_quad[2]) {
+ if (utf[0] == f_utf_space_en_quad[0] && utf[1] == f_utf_space_en_quad[1] && utf[2] == f_utf_space_en_quad[2]) {
return f_true;
}
- if (character.byte_1 == f_utf_space_em[0] && character.byte_2 == f_utf_space_em[1] && character.byte_3 == f_utf_space_em[2]) {
+ if (utf[0] == f_utf_space_em[0] && utf[1] == f_utf_space_em[1] && utf[2] == f_utf_space_em[2]) {
return f_true;
}
- if (character.byte_1 == f_utf_space_em_quad[0] && character.byte_2 == f_utf_space_em_quad[1] && character.byte_3 == f_utf_space_em_quad[2]) {
+ if (utf[0] == f_utf_space_em_quad[0] && utf[1] == f_utf_space_em_quad[1] && utf[2] == f_utf_space_em_quad[2]) {
return f_true;
}
- if (character.byte_1 == f_utf_space_em_per_three[0] && character.byte_2 == f_utf_space_em_per_three[1] && character.byte_3 == f_utf_space_em_per_three[2]) {
+ if (utf[0] == f_utf_space_em_per_three[0] && utf[1] == f_utf_space_em_per_three[1] && utf[2] == f_utf_space_em_per_three[2]) {
return f_true;
}
- if (character.byte_1 == f_utf_space_em_per_four[0] && character.byte_2 == f_utf_space_em_per_four[1] && character.byte_3 == f_utf_space_em_per_four[2]) {
+ if (utf[0] == f_utf_space_em_per_four[0] && utf[1] == f_utf_space_em_per_four[1] && utf[2] == f_utf_space_em_per_four[2]) {
return f_true;
}
- if (character.byte_1 == f_utf_space_em_per_six[0] && character.byte_2 == f_utf_space_em_per_six[1] && character.byte_3 == f_utf_space_em_per_six[2]) {
+ if (utf[0] == f_utf_space_em_per_six[0] && utf[1] == f_utf_space_em_per_six[1] && utf[2] == f_utf_space_em_per_six[2]) {
return f_true;
}
- if (character.byte_1 == f_utf_space_figure[0] && character.byte_2 == f_utf_space_figure[1] && character.byte_3 == f_utf_space_figure[2]) {
+ if (utf[0] == f_utf_space_figure[0] && utf[1] == f_utf_space_figure[1] && utf[2] == f_utf_space_figure[2]) {
return f_true;
}
- if (character.byte_1 == f_utf_space_punctuation[0] && character.byte_2 == f_utf_space_punctuation[1] && character.byte_3 == f_utf_space_punctuation[2]) {
+ if (utf[0] == f_utf_space_punctuation[0] && utf[1] == f_utf_space_punctuation[1] && utf[2] == f_utf_space_punctuation[2]) {
return f_true;
}
- if (character.byte_1 == f_utf_space_thin[0] && character.byte_2 == f_utf_space_thin[1] && character.byte_3 == f_utf_space_thin[2]) {
+ if (utf[0] == f_utf_space_thin[0] && utf[1] == f_utf_space_thin[1] && utf[2] == f_utf_space_thin[2]) {
return f_true;
}
- if (character.byte_1 == f_utf_space_hair[0] && character.byte_2 == f_utf_space_hair[1] && character.byte_3 == f_utf_space_hair[2]) {
+ if (utf[0] == f_utf_space_hair[0] && utf[1] == f_utf_space_hair[1] && utf[2] == f_utf_space_hair[2]) {
return f_true;
}
- if (character.byte_1 == f_utf_space_separator_line[0] && character.byte_2 == f_utf_space_separator_line[1] && character.byte_3 == f_utf_space_separator_line[2]) {
+ if (utf[0] == f_utf_space_separator_line[0] && utf[1] == f_utf_space_separator_line[1] && utf[2] == f_utf_space_separator_line[2]) {
return f_true;
}
- if (character.byte_1 == f_utf_space_separator_paragraph[0] && character.byte_2 == f_utf_space_separator_paragraph[1] && character.byte_3 == f_utf_space_separator_paragraph[2]) {
+ if (utf[0] == f_utf_space_separator_paragraph[0] && utf[1] == f_utf_space_separator_paragraph[1] && utf[2] == f_utf_space_separator_paragraph[2]) {
return f_true;
}
- if (character.byte_1 == f_utf_space_ogham[0] && character.byte_2 == f_utf_space_ogham[1] && character.byte_3 == f_utf_space_ogham[2]) {
+ if (utf[0] == f_utf_space_ogham[0] && utf[1] == f_utf_space_ogham[1] && utf[2] == f_utf_space_ogham[2]) {
return f_true;
}
- if (character.byte_1 == f_utf_space_ideographic[0] && character.byte_2 == f_utf_space_ideographic[1] && character.byte_3 == f_utf_space_ideographic[2]) {
+ if (utf[0] == f_utf_space_ideographic[0] && utf[1] == f_utf_space_ideographic[1] && utf[2] == f_utf_space_ideographic[2]) {
return f_true;
}
- if (character.byte_1 == f_utf_space_medium_mathematical[0] && character.byte_2 == f_utf_space_medium_mathematical[1] && character.byte_3 == f_utf_space_medium_mathematical[2]) {
+ if (utf[0] == f_utf_space_medium_mathematical[0] && utf[1] == f_utf_space_medium_mathematical[1] && utf[2] == f_utf_space_medium_mathematical[2]) {
return f_true;
}
- if (character.byte_1 == f_utf_substitute_symbol_blank[0] && character.byte_2 == f_utf_substitute_symbol_blank[1] && character.byte_3 == f_utf_substitute_symbol_blank[2]) {
+ if (utf[0] == f_utf_substitute_symbol_blank[0] && utf[1] == f_utf_substitute_symbol_blank[1] && utf[2] == f_utf_substitute_symbol_blank[2]) {
return f_true;
}
- if (character.byte_1 == f_utf_substitute_symbol_space[0] && character.byte_2 == f_utf_substitute_symbol_space[1] && character.byte_3 == f_utf_substitute_symbol_space[2]) {
+ if (utf[0] == f_utf_substitute_symbol_space[0] && utf[1] == f_utf_substitute_symbol_space[1] && utf[2] == f_utf_substitute_symbol_space[2]) {
return f_true;
}
- if (character.byte_1 == f_utf_substitute_open_box[0] && character.byte_2 == f_utf_substitute_open_box[1] && character.byte_3 == f_utf_substitute_open_box[2]) {
+ if (utf[0] == f_utf_substitute_open_box[0] && utf[1] == f_utf_substitute_open_box[1] && utf[2] == f_utf_substitute_open_box[2]) {
return f_true;
}
- if (character.byte_1 == f_utf_substitute_open_box_shouldered[0] && character.byte_2 == f_utf_substitute_open_box_shouldered[1] && character.byte_3 == f_utf_substitute_open_box_shouldered[2]) {
+ if (utf[0] == f_utf_substitute_open_box_shouldered[0] && utf[1] == f_utf_substitute_open_box_shouldered[1] && utf[2] == f_utf_substitute_open_box_shouldered[2]) {
return f_true;
}
#ifndef _di_f_utf_is_substitute_character_
f_return_status f_utf_is_substitute_character(const f_utf_character character) {
- f_u_short width = f_macro_utf_byte_width(character.byte_1);
+ f_u_short width = f_macro_utf_character_width(character);
if (width == 1) {
return f_false;
}
if (width == 2) {
- if (character.byte_1 == f_utf_substitute_middle_dot[0] && character.byte_2 == f_utf_substitute_middle_dot[1]) {
+ char utf[2] = { f_macro_utf_character_to_char_1(character), f_macro_utf_character_to_char_2(character) };
+
+ if (utf[0] == f_utf_substitute_middle_dot[0] && utf[1] == f_utf_substitute_middle_dot[1]) {
return f_true;
}
}
if (width == 3) {
- if (character.byte_1 == f_utf_substitute_symbol_blank[0] && character.byte_2 == f_utf_substitute_symbol_blank[1] && character.byte_3 == f_utf_substitute_symbol_blank[2]) {
+ char utf[3] = { f_macro_utf_character_to_char_1(character), f_macro_utf_character_to_char_2(character), f_macro_utf_character_to_char_3(character) };
+
+ if (utf[0] == f_utf_substitute_symbol_blank[0] && utf[1] == f_utf_substitute_symbol_blank[1] && utf[2] == f_utf_substitute_symbol_blank[2]) {
return f_true;
}
- if (character.byte_1 == f_utf_substitute_symbol_space[0] && character.byte_2 == f_utf_substitute_symbol_space[1] && character.byte_3 == f_utf_substitute_symbol_space[2]) {
+ if (utf[0] == f_utf_substitute_symbol_space[0] && utf[1] == f_utf_substitute_symbol_space[1] && utf[2] == f_utf_substitute_symbol_space[2]) {
return f_true;
}
- if (character.byte_1 == f_utf_substitute_open_box[0] && character.byte_2 == f_utf_substitute_open_box[1] && character.byte_3 == f_utf_substitute_open_box[2]) {
+ if (utf[0] == f_utf_substitute_open_box[0] && utf[1] == f_utf_substitute_open_box[1] && utf[2] == f_utf_substitute_open_box[2]) {
return f_true;
}
- if (character.byte_1 == f_utf_substitute_open_box_shouldered[0] && character.byte_2 == f_utf_substitute_open_box_shouldered[1] && character.byte_3 == f_utf_substitute_open_box_shouldered[2]) {
+ if (utf[0] == f_utf_substitute_open_box_shouldered[0] && utf[1] == f_utf_substitute_open_box_shouldered[1] && utf[2] == f_utf_substitute_open_box_shouldered[2]) {
return f_true;
}
#ifndef _di_f_utf_is_whitespace_character_
f_return_status f_utf_is_whitespace_character(const f_utf_character character) {
- f_u_short width = f_macro_utf_byte_width(character.byte_1);
+ f_u_short width = f_macro_utf_character_width(character);
if (width == 1) {
return f_false;
}
if (width == 2) {
- if (character.byte_1 == f_utf_space_no_break[0] && character.byte_2 == f_utf_space_no_break[1]) {
+ char utf[2] = { f_macro_utf_character_to_char_1(character), f_macro_utf_character_to_char_2(character) };
+
+ if (utf[0] == f_utf_space_no_break[0] && utf[1] == f_utf_space_no_break[1]) {
return f_true;
}
- if (character.byte_1 == f_utf_space_line_feed_reverse[0] && character.byte_2 == f_utf_space_line_feed_reverse[1]) {
+ if (utf[0] == f_utf_space_line_feed_reverse[0] && utf[1] == f_utf_space_line_feed_reverse[1]) {
return f_true;
}
- if (character.byte_1 == f_utf_space_line_next[0] && character.byte_2 == f_utf_space_line_next[1]) {
+ if (utf[0] == f_utf_space_line_next[0] && utf[1] == f_utf_space_line_next[1]) {
return f_true;
}
}
if (width == 3) {
- if (character.byte_1 == f_utf_space_no_break_narrow[0] && character.byte_2 == f_utf_space_no_break_narrow[1] && character.byte_3 == f_utf_space_no_break_narrow[2]) {
+ char utf[3] = { f_macro_utf_character_to_char_1(character), f_macro_utf_character_to_char_2(character), f_macro_utf_character_to_char_3(character) };
+
+ if (utf[0] == f_utf_space_no_break_narrow[0] && utf[1] == f_utf_space_no_break_narrow[1] && utf[2] == f_utf_space_no_break_narrow[2]) {
return f_true;
}
- if (character.byte_1 == f_utf_space_en[0] && character.byte_2 == f_utf_space_en[1] && character.byte_3 == f_utf_space_en[2]) {
+ if (utf[0] == f_utf_space_en[0] && utf[1] == f_utf_space_en[1] && utf[2] == f_utf_space_en[2]) {
return f_true;
}
- if (character.byte_1 == f_utf_space_en_quad[0] && character.byte_2 == f_utf_space_en_quad[1] && character.byte_3 == f_utf_space_en_quad[2]) {
+ if (utf[0] == f_utf_space_en_quad[0] && utf[1] == f_utf_space_en_quad[1] && utf[2] == f_utf_space_en_quad[2]) {
return f_true;
}
- if (character.byte_1 == f_utf_space_en_quad[0] && character.byte_2 == f_utf_space_en_quad[1] && character.byte_3 == f_utf_space_en_quad[2]) {
+ if (utf[0] == f_utf_space_en_quad[0] && utf[1] == f_utf_space_en_quad[1] && utf[2] == f_utf_space_en_quad[2]) {
return f_true;
}
- if (character.byte_1 == f_utf_space_em[0] && character.byte_2 == f_utf_space_em[1] && character.byte_3 == f_utf_space_em[2]) {
+ if (utf[0] == f_utf_space_em[0] && utf[1] == f_utf_space_em[1] && utf[2] == f_utf_space_em[2]) {
return f_true;
}
- if (character.byte_1 == f_utf_space_em_quad[0] && character.byte_2 == f_utf_space_em_quad[1] && character.byte_3 == f_utf_space_em_quad[2]) {
+ if (utf[0] == f_utf_space_em_quad[0] && utf[1] == f_utf_space_em_quad[1] && utf[2] == f_utf_space_em_quad[2]) {
return f_true;
}
- if (character.byte_1 == f_utf_space_em_per_three[0] && character.byte_2 == f_utf_space_em_per_three[1] && character.byte_3 == f_utf_space_em_per_three[2]) {
+ if (utf[0] == f_utf_space_em_per_three[0] && utf[1] == f_utf_space_em_per_three[1] && utf[2] == f_utf_space_em_per_three[2]) {
return f_true;
}
- if (character.byte_1 == f_utf_space_em_per_four[0] && character.byte_2 == f_utf_space_em_per_four[1] && character.byte_3 == f_utf_space_em_per_four[2]) {
+ if (utf[0] == f_utf_space_em_per_four[0] && utf[1] == f_utf_space_em_per_four[1] && utf[2] == f_utf_space_em_per_four[2]) {
return f_true;
}
- if (character.byte_1 == f_utf_space_em_per_six[0] && character.byte_2 == f_utf_space_em_per_six[1] && character.byte_3 == f_utf_space_em_per_six[2]) {
+ if (utf[0] == f_utf_space_em_per_six[0] && utf[1] == f_utf_space_em_per_six[1] && utf[2] == f_utf_space_em_per_six[2]) {
return f_true;
}
- if (character.byte_1 == f_utf_space_figure[0] && character.byte_2 == f_utf_space_figure[1] && character.byte_3 == f_utf_space_figure[2]) {
+ if (utf[0] == f_utf_space_figure[0] && utf[1] == f_utf_space_figure[1] && utf[2] == f_utf_space_figure[2]) {
return f_true;
}
- if (character.byte_1 == f_utf_space_punctuation[0] && character.byte_2 == f_utf_space_punctuation[1] && character.byte_3 == f_utf_space_punctuation[2]) {
+ if (utf[0] == f_utf_space_punctuation[0] && utf[1] == f_utf_space_punctuation[1] && utf[2] == f_utf_space_punctuation[2]) {
return f_true;
}
- if (character.byte_1 == f_utf_space_thin[0] && character.byte_2 == f_utf_space_thin[1] && character.byte_3 == f_utf_space_thin[2]) {
+ if (utf[0] == f_utf_space_thin[0] && utf[1] == f_utf_space_thin[1] && utf[2] == f_utf_space_thin[2]) {
return f_true;
}
- if (character.byte_1 == f_utf_space_hair[0] && character.byte_2 == f_utf_space_hair[1] && character.byte_3 == f_utf_space_hair[2]) {
+ if (utf[0] == f_utf_space_hair[0] && utf[1] == f_utf_space_hair[1] && utf[2] == f_utf_space_hair[2]) {
return f_true;
}
- if (character.byte_1 == f_utf_space_separator_line[0] && character.byte_2 == f_utf_space_separator_line[1] && character.byte_3 == f_utf_space_separator_line[2]) {
+ if (utf[0] == f_utf_space_separator_line[0] && utf[1] == f_utf_space_separator_line[1] && utf[2] == f_utf_space_separator_line[2]) {
return f_true;
}
- if (character.byte_1 == f_utf_space_separator_paragraph[0] && character.byte_2 == f_utf_space_separator_paragraph[1] && character.byte_3 == f_utf_space_separator_paragraph[2]) {
+ if (utf[0] == f_utf_space_separator_paragraph[0] && utf[1] == f_utf_space_separator_paragraph[1] && utf[2] == f_utf_space_separator_paragraph[2]) {
return f_true;
}
- if (character.byte_1 == f_utf_space_ogham[0] && character.byte_2 == f_utf_space_ogham[1] && character.byte_3 == f_utf_space_ogham[2]) {
+ if (utf[0] == f_utf_space_ogham[0] && utf[1] == f_utf_space_ogham[1] && utf[2] == f_utf_space_ogham[2]) {
return f_true;
}
- if (character.byte_1 == f_utf_space_ideographic[0] && character.byte_2 == f_utf_space_ideographic[1] && character.byte_3 == f_utf_space_ideographic[2]) {
+ if (utf[0] == f_utf_space_ideographic[0] && utf[1] == f_utf_space_ideographic[1] && utf[2] == f_utf_space_ideographic[2]) {
return f_true;
}
- if (character.byte_1 == f_utf_space_medium_mathematical[0] && character.byte_2 == f_utf_space_medium_mathematical[1] && character.byte_3 == f_utf_space_medium_mathematical[2]) {
+ if (utf[0] == f_utf_space_medium_mathematical[0] && utf[1] == f_utf_space_medium_mathematical[1] && utf[2] == f_utf_space_medium_mathematical[2]) {
return f_true;
}
}
#endif // _di_f_utf_is_whitespace_character_
-#ifndef _di_f_utf_string_to_character_
- f_return_status f_utf_string_to_character(const f_string character_string, const f_u_short max_width, f_utf_character *utf_character) {
+#ifndef _di_f_utf_char_to_character_
+ f_return_status f_utf_char_to_character(const f_string character, const f_u_short max_width, f_utf_character *utf_character) {
#ifndef _di_level_0_parameter_checking_
if (max_width < 1) return f_error_set_error(f_invalid_parameter);
+ if (utf_character == 0) return f_error_set_error(f_invalid_parameter);
#endif // _di_level_0_parameter_checking_
- f_u_short width = f_macro_utf_byte_width_is(character_string[0]);
+ f_u_short width = f_macro_utf_byte_width(*character);
+
+ if (width == 1) {
+ *utf_character = f_macro_utf_character_from_char_1(character[0]);
+ return f_none;
+ }
- if (width >= max_width) {
+ if (width > max_width) {
return f_error_set_error(f_failure);
}
memset(utf_character, 0, sizeof(f_utf_character));
- utf_character->byte_1 = character_string[0];
+ *utf_character |= f_macro_utf_character_to_char_1(character[0]);
if (width < 2) {
return f_none;
}
- utf_character->byte_2 = character_string[1];
+ *utf_character |= f_macro_utf_character_to_char_2(character[1]);
if (width == 2) {
return f_none;
}
- utf_character->byte_3 = character_string[2];
+ *utf_character |= f_macro_utf_character_to_char_3(character[2]);
if (width == 3) {
return f_none;
}
- utf_character->byte_4 = character_string[3];
+ *utf_character |= f_macro_utf_character_to_char_4(character[3]);
return f_none;
}
-#endif // _di_f_utf_string_to_character_
+#endif // _di_f_utf_char_to_character_
#ifdef __cplusplus
} // extern "C"
#endif // _di_f_utf_bom_
/**
- * Provide a basic UTF-8 character.
- *
- * This is intended to be used so that a single path parameter can be passed to a function instead of an array of characters.
- */
-#ifndef _di_f_utf_character_
- typedef struct {
- char byte_1;
- char byte_2;
- char byte_3;
- char byte_4;
- } f_utf_character;
-
- #define f_utf_character_initialize \
- { \
- '\0', \
- '\0', \
- '\0', \
- '\0', \
- }
-#endif // _di_f_utf_char_
-
-/**
* Define the UTF-8 bytes.
*
* The bytes are for checking a single 8-bit character value (specifically, checking the first bits).
* The f_macro_utf_byte_is_* macros are used to determine a width of the character (either 1, 2, 3, or 4, respectively).
*
* The f_macro_utf_byte_width macro determines a width of the character.
- *
* The f_macro_utf_byte_width_is is identical to f_macro_utf_byte_width, except it returns 0 when character is not UTF-8.
*/
#ifndef _di_f_utf_byte_
#endif // _di_f_utf_byte_
/**
+ * Provide a basic UTF-8 character as a single 4-byte variable.
+ *
+ * This is intended to be used when a single variable is desired to represent a 1-byte, 2-byte, 3-byte, or even 4-byte character.
+ *
+ * The byte structure is intended to be read left to right.
+ *
+ * The f_macro_utf_character_mask_byte_* are used to get the entire character set fo a given width.
+ *
+ * The f_macro_utf_character_mask_char_* are used to get a specific UTF-8 block as a single character range.
+ *
+ * The f_macro_utf_character_to_char_* are used to convert a f_utf_character into a char, for a given 8-bit block.
+ *
+ * The f_macro_utf_character_from_char_* are used to convert a char into part of a f_utf_character, for a given 8-bit block.
+ *
+ * The f_macro_utf_character_width is used to determine the width of the UTF-8 character based on f_macro_utf_byte_width.
+ * The f_macro_utf_character_width_is is used to determine the width of the UTF-8 character based on f_macro_utf_byte_width_is.
+ */
+#ifndef _di_f_utf_character_
+ typedef uint32_t f_utf_character;
+
+ #define f_macro_utf_character_mask_bom 0xefbbbf00 // 1110 1111, 1011 1011, 1011 1111, 0000 0000
+
+ #define f_macro_utf_character_mask_byte_1 0xff000000 // 1111 1111, 0000 0000, 0000 0000, 0000 0000
+ #define f_macro_utf_character_mask_byte_2 0xffff0000 // 1111 1111, 1111 1111, 0000 0000, 0000 0000
+ #define f_macro_utf_character_mask_byte_3 0xffffff00 // 1111 1111, 1111 1111, 1111 1111, 0000 0000
+ #define f_macro_utf_character_mask_byte_4 0xffffffff // 1111 1111, 1111 1111, 1111 1111, 1111 1111
+
+ #define f_macro_utf_character_mask_char_1 0xff000000 // 1111 1111, 0000 0000, 0000 0000, 0000 0000
+ #define f_macro_utf_character_mask_char_2 0x00ff0000 // 0000 0000, 1111 1111, 0000 0000, 0000 0000
+ #define f_macro_utf_character_mask_char_3 0x0000ff00 // 0000 0000, 0000 0000, 1111 1111, 0000 0000
+ #define f_macro_utf_character_mask_char_4 0x000000ff // 0000 0000, 0000 0000, 0000 0000, 1111 1111
+
+ #define f_macro_utf_character_to_char_1(character) ((f_macro_utf_character_mask_char_1 & character) >> 24) // grab first byte.
+ #define f_macro_utf_character_to_char_2(character) ((f_macro_utf_character_mask_char_2 & character) >> 16) // grab second byte.
+ #define f_macro_utf_character_to_char_3(character) ((f_macro_utf_character_mask_char_3 & character) >> 8) // grab third byte.
+ #define f_macro_utf_character_to_char_4(character) (f_macro_utf_character_mask_char_4 & character) // grab fourth byte.
+
+ #define f_macro_utf_character_from_char_1(character) (character << 24) // shift the first byte.
+ #define f_macro_utf_character_from_char_2(character) (character << 16) // shift the second byte.
+ #define f_macro_utf_character_from_char_3(character) (character << 8) // shift the third byte.
+ #define f_macro_utf_character_from_char_4(character) (character) // shift the fourth byte.
+
+ #define f_macro_utf_character_width(character) (f_macro_utf_byte_width(f_macro_utf_character_to_char_1(character)))
+ #define f_macro_utf_character_width_is(character) (f_macro_utf_byte_width_is(f_macro_utf_character_to_char_1(character)))
+#endif // _di_f_utf_character_
+
+/**
* Define the UTF-8 general whitespace codes.
*
* These are integers representing character codes that represent types of spaces.
* f_maybe (with error bit) if this could be a whitespace or substitute but width is not long enough.
* f_invalid_parameter (with error bit) if a parameter is invalid.
*/
-#ifndef _di_f_utf_is_bom_string_
- extern f_return_status f_utf_is_bom_string(const f_string character, const f_u_short max_width);
-#endif // _di_f_utf_is_bom_string_
+#ifndef _di_f_utf_is_bom_
+ extern f_return_status f_utf_is_bom(const f_string character, const f_u_short max_width);
+#endif // _di_f_utf_is_bom_
/**
* Check to see if the entire byte block of the character is a UTF-8 printable character.
* f_maybe (with error bit) if this could be a graph but width is not long enough.
* f_invalid_parameter (with error bit) if a parameter is invalid.
*/
-#ifndef _di_f_utf_is_graph_string_
- extern f_return_status f_utf_is_graph_string(const f_string character, const f_u_short max_width);
-#endif // _di_f_utf_is_graph_string_
+#ifndef _di_f_utf_is_graph_
+ extern f_return_status f_utf_is_graph(const f_string character, const f_u_short max_width);
+#endif // _di_f_utf_is_graph_
/**
* Check to see if the entire byte block of the character is a UTF-8 whitespace or substitute character.
* f_maybe (with error bit) if this could be a whitespace or substitute but width is not long enough.
* f_invalid_parameter (with error bit) if a parameter is invalid.
*/
-#ifndef _di_f_utf_is_space_string_
- extern f_return_status f_utf_is_space_string(const f_string character, const f_u_short max_width);
-#endif // _di_f_utf_is_space_string_
+#ifndef _di_f_utf_is_space_
+ extern f_return_status f_utf_is_space(const f_string character, const f_u_short max_width);
+#endif // _di_f_utf_is_space_
/**
* Check to see if the entire byte block of the character is a UTF-8 whitespace substitute character.
* f_maybe (with error bit) if this could be a substitute but width is not long enough.
* f_invalid_parameter (with error bit) if a parameter is invalid.
*/
-#ifndef _di_f_utf_is_substitute_string_
- extern f_return_status f_utf_is_substitute_string(const f_string character, const f_u_short max_width);
-#endif // _di_f_utf_is_substitute_string_
+#ifndef _di_f_utf_is_substitute_
+ extern f_return_status f_utf_is_substitute(const f_string character, const f_u_short max_width);
+#endif // _di_f_utf_is_substitute_
/**
* Check to see if the entire byte block of the character is a UTF-8 general whitespace character.
* f_maybe (with error bit) if this could be a whitespace but width is not long enough.
* f_invalid_parameter (with error bit) if a parameter is invalid.
*/
-#ifndef _di_f_utf_is_whitespace_string_
- extern f_return_status f_utf_is_whitespace_string(const f_string character, const f_u_short max_width);
-#endif // _di_f_utf_is_whitespace_string_
+#ifndef _di_f_utf_is_whitespace_
+ extern f_return_status f_utf_is_whitespace(const f_string character, const f_u_short max_width);
+#endif // _di_f_utf_is_whitespace_
/**
* Check to see if the entire byte block of the character is a UTF-8 BOM.
*
* This will also convert ASCII characters.
*
- * @param character_string
+ * @param character
* The character string to be converted to the f_utf_character type.
* There must be enough space allocated to convert against, as limited by max_width.
* @param max_width
* f_failure (with error bit) if width is not long enough to convert.
* f_invalid_parameter (with error bit) if a parameter is invalid.
*/
-#ifndef _di_f_utf_string_to_character_
- extern f_return_status f_utf_string_to_character(const f_string character_string, const f_u_short max_width, f_utf_character *utf_character);
-#endif // _di_f_utf_string_to_character_
+#ifndef _di_f_utf_char_to_character_
+ extern f_return_status f_utf_char_to_character(const f_string character, const f_u_short max_width, f_utf_character *utf_character);
+#endif // _di_f_utf_char_to_character_
#ifdef __cplusplus
} // extern "C"
// A single UTF-8 BOM is allowed to exist before the valid FSS identifier.
if (buffer.used > 3) {
- f_status status = f_utf_is_bom_string(buffer.string, 4);
+ f_status status = f_utf_is_bom(buffer.string, 4);
if (f_error_is_error(status)) {
return f_error_set_error(fl_fss_no_header);
max_width = buffer.used - input.start;
}
- f_status status = f_utf_is_space_string(buffer.string + input.start, max_width);
+ f_status status = f_utf_is_space(buffer.string + input.start, max_width);
if (f_error_is_error(status)) {
return status;
max_width = buffer.used - input.start;
}
- f_status status = f_utf_is_space_string(buffer.string + input.start, max_width);
+ f_status status = f_utf_is_space(buffer.string + input.start, max_width);
if (f_error_is_error(status)) {
return status;
if (buffer.string[input->start] != f_fss_delimit_placeholder) {
max_width = (input->stop - input->start) + 1;
- if (f_utf_is_space_string(buffer.string +input->start, max_width) != f_true) {
- if (f_utf_is_bom_string(buffer.string + input->start, max_width) != f_true) {
+ if (f_utf_is_space(buffer.string +input->start, max_width) != f_true) {
+ if (f_utf_is_bom(buffer.string + input->start, max_width) != f_true) {
break;
}
}
if (buffer.string[input->start] != f_fss_delimit_placeholder) {
max_width = (input->stop - input->start) + 1;
- if (f_utf_is_space_string(buffer.string + input->start, max_width) != f_true) {
- if (f_utf_is_bom_string(buffer.string + input->start, max_width) != f_true) {
+ if (f_utf_is_space(buffer.string + input->start, max_width) != f_true) {
+ if (f_utf_is_bom(buffer.string + input->start, max_width) != f_true) {
break;
}
}
*
* @return
* f_none on success.
- * f_none_on_stop if the stop point is reached before all steps are completed.
+ * f_none_on_stop if the stop location is reached before all steps are completed.
* f_none_on_eos if the end of buffer is reached before all steps are completed.
* f_invalid_parameter (with error bit) if a parameter is invalid.
- * f_incomplete_utf_on_stop (with error bit) if the stop point is reached before the complete UTF-8 character can be processed.
+ * f_incomplete_utf_on_stop (with error bit) if the stop location is reached before the complete UTF-8 character can be processed.
* f_incomplete_utf_on_eos (with error bit) if the end of buffer is reached before the complete UTF-8 character can be processed.
*/
#ifndef _di_fl_fss_decrement_buffer_
*
* @return
* f_none on success.
- * f_none_on_stop if the stop point is reached before all steps are completed.
+ * f_none_on_stop if the stop location is reached before all steps are completed.
* f_none_on_eos if the end of buffer is reached before all steps are completed.
* f_invalid_parameter (with error bit) if a parameter is invalid.
- * f_incomplete_utf_on_stop (with error bit) if the stop point is reached before the complete UTF-8 character can be processed.
+ * f_incomplete_utf_on_stop (with error bit) if the stop location is reached before the complete UTF-8 character can be processed.
* f_incomplete_utf_on_eos (with error bit) if the end of buffer is reached before the complete UTF-8 character can be processed.
*/
#ifndef _di_fl_fss_increment_buffer_
++input->start;
} while (f_true);
- // Save the stop point
+ // Save the stop location
found->array[found->used].stop = input->start - 1;
found->used++;
f_status status = f_none;
-
if (serialized->used + value.used + 1 >= serialized->size) {
- f_resize_dynamic_string(status, (*serialized), serialized->size + value.used + f_serialized_default_allocation_step);
+ f_resize_dynamic_string(status, (*serialized), serialized->size + value.used + 1);
if (f_error_is_error(status)) return status;
}
}
#endif // _di_fl_serialize_simple_
-#ifndef _di_fl_unserialize_simple_
- f_return_status fl_unserialize_simple(const f_dynamic_string serialized, f_string_locations *locations) {
+#ifndef _di_fl_unserialize_simple_map_
+ f_return_status fl_unserialize_simple_map(const f_dynamic_string serialized, f_string_locations *locations) {
#ifndef _di_level_0_parameter_checking_
if (locations == 0) return f_error_set_error(f_invalid_parameter);
#endif // _di_level_0_parameter_checking_
f_array_length i = 0;
f_array_length start = 0;
- while (i <= serialized.used) {
+ f_u_short width = 0;
+
+ while (i < serialized.used) {
+ width = f_macro_utf_byte_width(serialized.string[i]);
+
if (serialized.string[i] == f_serialized_simple_splitter || i == serialized.used) {
- if (locations->used + 1 >= locations->size) {
+ if (locations->used + width >= locations->size) {
f_resize_string_locations(status, (*locations), locations->size + f_serialized_default_allocation_step);
if (f_error_is_error(status)) return status;
}
if (start == i) {
+ // provide an invalid start to stop range to communicate that there is no data.
locations->array[locations->used].start = 1;
locations->array[locations->used].stop = 0;
locations->used++;
locations->used++;
}
- start = i + 1;
+ if (i + width > serialized.used) {
+ return f_error_set_error(f_incomplete_utf_on_eos);
+ }
+
+ start = i + width;
+ }
+ else if (i + width > serialized.used) {
+ return f_error_set_error(f_incomplete_utf_on_eos);
}
- i++;
+ i += width;
} // while
return f_none;
}
-#endif // _di_fl_unserialize_simple_
+#endif // _di_fl_unserialize_simple_map_
-#ifndef _di_fl_unserialize_simple_get_
- f_return_status fl_unserialize_simple_get(const f_dynamic_string serialized, const f_array_length index, f_string_location *location) {
+#ifndef _di_fl_unserialize_simple_find_
+ f_return_status fl_unserialize_simple_find(const f_dynamic_string serialized, const f_array_length index, f_string_location *location) {
#ifndef _di_level_0_parameter_checking_
if (location == 0) return f_error_set_error(f_invalid_parameter);
#endif // _di_level_0_parameter_checking_
f_status status = f_none;
f_array_length i = 0;
+ f_array_length start = 0;
f_array_length current = 0;
- location->start = 1;
- location->stop = 0;
+ f_u_short width = 0;
while (i < serialized.used) {
- if (current == index) {
- if (location->start > location->stop) {
- location->start = i;
- location->stop = i;
+ width = f_macro_utf_byte_width(serialized.string[i]);
+
+ if (serialized.string[i] == f_serialized_simple_splitter) {
+ if (current == index) {
+ if (start == i) {
+ // provide an invalid start to stop range to communicate that there is no data.
+ location->start = 1;
+ location->stop = 0;
+ }
+ else {
+ location->start = start;
+ location->stop = i - 1;
+ }
+
+ return f_none;
}
- if (serialized.string[i] == f_serialized_simple_splitter) {
+ start = i + width;
+ current++;
+ }
+ else if (i == serialized.used) {
+ if (current == index) {
+ location->start = start;
location->stop = i - 1;
- break;
}
+
+ return f_none_on_eos;
}
- else if (serialized.string[i] == f_serialized_simple_splitter) {
- current++;
+
+ if (i + width > serialized.used) {
+ return f_error_set_error(f_incomplete_utf_on_eos);
}
- i++;
+ i += width;
} // while
- return f_none;
+ return f_no_data_on_eos;
}
-#endif // _di_fl_unserialize_simple_get_
+#endif // _di_fl_unserialize_simple_find_
#ifdef __cplusplus
} // extern "C"
#include <level_0/serialized.h>
#include <level_0/strings.h>
#include <level_0/types.h>
+#include <level_0/utf.h>
#ifdef __cplusplus
extern "C" {
#endif
+/**
+ * Serialized a string using the Simple serialize algorithm.
+ *
+ * The simple Serialize algorithm is akin to the PATH environment variable, example: PATH="/bin:/sbin:/usr/bin".
+ *
+ * To generate the above example, this would be called 3 times, with the following strings:
+ * 1) value = "/bin", then: PATH="/bin".
+ * 2) value = "/sbin", then: PATH="/bin:/sbin".
+ * 3) value = "/usr/sbin", then: PATH="/bin:/sbin:/usr/sbin".
+ *
+ * @param value
+ * The string to append onto serialized.
+ * @param serialized
+ * The dynamic string that represents a serialized set of strings.
+ *
+ * @return
+ * f_none on success.
+ * f_invalid_parameter (with error bit) if a parameter is invalid.
+ * f_reallocation_error (with error bit) on memory reallocation error.
+ */
#ifndef _di_fl_serialize_simple_
- /**
- * this function will append a string to the serialize.
- */
extern f_return_status fl_serialize_simple(const f_dynamic_string value, f_dynamic_string *serialized);
#endif // _di_fl_serialize_simple_
-#ifndef _di_fl_unserialize_simple_
- /**
- * this function will unserialize a serialized string and store the results in an array of strings.
- */
- extern f_return_status fl_unserialize_simple(const f_dynamic_string serialized, f_string_locations *locations);
-#endif // _di_fl_unserialize_
-
-#ifndef _di_fl_unserialize_simple_get_
- /**
- * this function will pull a single serialized value from the serialized string at the given index.
- */
- extern f_return_status fl_unserialize_simple_get(const f_dynamic_string serialized, const f_array_length index, f_string_location *location);
-#endif // _di_fl_unserialize_simple_get_
+// @todo: implement fl_unserialize_simple() such that a new array of strings is allocated.
+
+/**
+ * Identify string positions within a serialized string using the Simple serialize algorithm.
+ *
+ * The simple Serialize algorithm is akin to the PATH environment variable, example: PATH="/bin:/sbin:/usr/bin".
+ *
+ * After processing the above example, there would be the following positions:
+ * 1) start = 0, stop = 3.
+ * 2) start = 5, stop = 9.
+ * 3) start = 11, stop = 18.
+ *
+ * @param serialized
+ * A serialized string to de-serialize.
+ * @param locations
+ * The locations within the serialized string representing distinct separate strings.
+ *
+ * @return
+ * f_none on success.
+ * f_incomplete_utf_on_eos if end of sting is reached before a complete UTF-8 character can be processed.
+ * f_invalid_parameter (with error bit) if a parameter is invalid.
+ * f_reallocation_error (with error bit) on memory reallocation error.
+ */
+#ifndef _di_fl_unserialize_simple_map_
+ extern f_return_status fl_unserialize_simple_map(const f_dynamic_string serialized, f_string_locations *locations);
+#endif // _di_fl_unserialize_simple_map_
+
+/**
+ * Unserialize a specific string using the Simple serialize algorithm.
+ *
+ * The simple Serialize algorithm is akin to the PATH environment variable, example: PATH="/bin:/sbin:/usr/bin".
+ *
+ * After processing the above example, there would be the following positions, for the given index:
+ * 1) with index = 0, start = 0, stop = 3.
+ * 2) with index = 1, start = 5, stop = 9.
+ * 3) with index = 2, start = 11, stop = 18.
+ *
+ * @param serialized
+ * A serialized string to de-serialize.
+ * @param index
+ * An index position within the serialized string to get the deserialized positions of.
+ * @param location
+ * A location within the serialized string representing the string at the given index.
+ *
+ * @return
+ * f_none on success.
+ * f_none_on_eos on success at end of string.
+ * f_no_data_on_eos if end of string reached before index was reached.
+ * f_incomplete_utf_on_eos (with error bit) if end of string is reached before a complete UTF-8 character can be processed.
+ * f_invalid_parameter (with error bit) if a parameter is invalid.
+ */
+#ifndef _di_fl_unserialize_simple_find_
+ extern f_return_status fl_unserialize_simple_find(const f_dynamic_string serialized, const f_array_length index, f_string_location *location);
+#endif // _di_fl_unserialize_simple_find_
+
+// @todo: implement fl_unserialize_simple_get() such that a new string is allocated, if found.
#ifdef __cplusplus
} // extern "C"
f_strings
f_serialized
f_memory
+f_utf
build_compiler gcc
build_linker ar
build_libraries -lc
-build_libraries_fll -lf_memory
+build_libraries_fll -lf_memory -lf_utf
build_sources_library serialized.c
-build_sources_program
+build_sources_program
build_sources_headers serialized.h
build_sources_bash
build_sources_settings
extern "C" {
#endif
-// TODO: this file needs to be rewriten with UTF-8 support.
-
#ifndef _di_fl_rip_string_
- f_return_status fl_rip_string(const f_dynamic_string buffer, const f_string_location position, f_dynamic_string *results) {
+ f_return_status fl_rip_string(const f_dynamic_string buffer, const f_string_location location, f_dynamic_string *result) {
#ifndef _di_level_1_parameter_checking_
- if (results == 0) return f_error_set_error(f_invalid_parameter);
- if (position.start < 0) return f_error_set_error(f_invalid_parameter);
- if (position.stop < position.start) return f_error_set_error(f_invalid_parameter);
+ if (location.start < 0) return f_error_set_error(f_invalid_parameter);
+ if (location.stop < location.start) return f_error_set_error(f_invalid_parameter);
if (buffer.used <= 0) return f_error_set_error(f_invalid_parameter);
- if (position.start >= buffer.used) return f_error_set_error(f_invalid_parameter);
+ if (location.start >= buffer.used) return f_error_set_error(f_invalid_parameter);
#endif // _di_level_1_parameter_checking_
// the start and stop point are inclusive locations, and therefore start - stop is actually 1 too few locations
- f_string_length size = position.stop - position.start + 1;
+ f_string_length size = (location.stop - location.start) + 1;
if (size > 0) {
f_status status = f_none;
- f_resize_dynamic_string(status, (*results), size);
+ if (result == 0) {
+ f_new_dynamic_string(status, (*result), size);
+ }
+ else {
+ f_resize_dynamic_string(status, (*result), size);
+ }
if (f_error_is_error(status)) {
return status;
}
- memcpy(results->string, buffer.string + position.start, sizeof(char) * size);
- results->used = size;
+ memcpy(result->string, buffer.string + location.start, sizeof(char) * size);
+ result->used = size;
return f_none;
}
}
#endif // _di_fl_rip_string_
-#ifndef _di_fl_seek_line_past_non_graph_
- f_return_status fl_seek_line_past_non_graph(const f_dynamic_string buffer, f_string_location *position, const char placeholder) {
+#ifndef _di_fl_seek_line_until_graph_
+ f_return_status fl_seek_line_until_graph(const f_dynamic_string buffer, f_string_location *location, const char placeholder) {
#ifndef _di_level_1_parameter_checking_
- if (position == 0) return f_error_set_error(f_invalid_parameter);
- if (position->start < 0) return f_error_set_error(f_invalid_parameter);
- if (position->stop < position->start) return f_error_set_error(f_invalid_parameter);
+ if (location == 0) return f_error_set_error(f_invalid_parameter);
+ if (location->start < 0) return f_error_set_error(f_invalid_parameter);
+ if (location->stop < location->start) return f_error_set_error(f_invalid_parameter);
if (buffer.used <= 0) return f_error_set_error(f_invalid_parameter);
- if (position->start >= buffer.used) return f_error_set_error(f_invalid_parameter);
+ if (location->start >= buffer.used) return f_error_set_error(f_invalid_parameter);
#endif // _di_level_1_parameter_checking_
- while (!isgraph(buffer.string[position->start]) || buffer.string[position->start] == placeholder) {
- if (buffer.string[position->start] == f_eol) return f_none;
+ f_status status = f_none;
+ f_u_short width = 0;
+
+ f_string_length max_width = (location->stop - location->start) + 1;
+
+ if (max_width > buffer.used - location->start) {
+ max_width = buffer.used - location->start;
+ }
+
+ while (buffer.string[location->start] == placeholder || (!isgraph(buffer.string[location->start]) && (status = f_utf_is_graph(buffer.string + location->start, max_width)) == f_false)) {
+ if (buffer.string[location->start] == f_eol) return f_none_on_eol;
+
+ width = f_macro_utf_byte_width(buffer.string[location->start]);
+
+ if (width > 1) {
+ if (location->start + width >= buffer.used) return f_error_set_error(f_incomplete_utf_on_eos);
+ if (location->start + width > location->stop) return f_error_set_error(f_incomplete_utf_on_stop);
+ }
+
+ location->start += width;
+
+ if (location->start >= buffer.used) return f_none_on_eos;
+ if (location->start > location->stop) return f_none_on_stop;
- ++position->start;
+ max_width = (location->stop - location->start) + 1;
- if (position->start >= buffer.used) return f_none_on_eos;
- if (position->start > position->stop) return f_none_on_stop;
+ if (max_width > buffer.used - location->start) {
+ max_width = buffer.used - location->start;
+ }
} // while
+ if (f_error_is_error(status)) {
+ return status;
+ }
+
return f_none;
}
-#endif // _di_fl_seek_line_past_non_graph_
+#endif // _di_fl_seek_line_until_graph_
#ifndef _di_fl_seek_line_until_non_graph_
- f_return_status fl_seek_line_until_non_graph(const f_dynamic_string buffer, f_string_location *position, const char placeholder) {
+ f_return_status fl_seek_line_until_non_graph(const f_dynamic_string buffer, f_string_location *location, const char placeholder) {
#ifndef _di_level_1_parameter_checking_
- if (position->start < 0) return f_error_set_error(f_invalid_parameter);
- if (position->stop < position->start) return f_error_set_error(f_invalid_parameter);
+ if (location == 0) return f_error_set_error(f_invalid_parameter);
+ if (location->start < 0) return f_error_set_error(f_invalid_parameter);
+ if (location->stop < location->start) return f_error_set_error(f_invalid_parameter);
if (buffer.used <= 0) return f_error_set_error(f_invalid_parameter);
- if (position->start >= buffer.used) return f_error_set_error(f_invalid_parameter);
+ if (location->start >= buffer.used) return f_error_set_error(f_invalid_parameter);
#endif // _di_level_1_parameter_checking_
- while (isgraph(buffer.string[position->start]) || buffer.string[position->start] == placeholder) {
- if (buffer.string[position->start] == f_eol) return f_none;
+ f_status status = f_none;
+ f_u_short width = 0;
+
+ f_string_length max_width = (location->stop - location->start) + 1;
+
+ if (max_width > buffer.used - location->start) {
+ max_width = buffer.used - location->start;
+ }
+
+ while (buffer.string[location->start] == placeholder || (isgraph(buffer.string[location->start]) && (status = f_utf_is_space(buffer.string + location->start, max_width)) == f_false)) {
+ if (buffer.string[location->start] == f_eol) return f_none_on_eol;
+
+ width = f_macro_utf_byte_width(buffer.string[location->start]);
+
+ if (width > 1) {
+ if (location->start + width >= buffer.used) return f_error_set_error(f_incomplete_utf_on_eos);
+ if (location->start + width > location->stop) return f_error_set_error(f_incomplete_utf_on_stop);
+ }
+
+ location->start += width;
- ++position->start;
+ if (location->start >= buffer.used) return f_none_on_eos;
+ if (location->start > location->stop) return f_none_on_stop;
- if (position->start >= buffer.used) return f_none_on_eos;
- if (position->start > position->stop) return f_none_on_stop;
+ max_width = (location->stop - location->start) + 1;
+
+ if (max_width > buffer.used - location->start) {
+ max_width = buffer.used - location->start;
+ }
} // while
+ if (f_error_is_error(status)) {
+ return status;
+ }
+
return f_none;
}
#endif // _di_fl_seek_line_until_non_graph_
-#ifndef _di_fl_seek_to_
- f_return_status fl_seek_to(const f_dynamic_string buffer, f_string_location *position, const char seek_to_this) {
+#ifndef _di_fl_seek_line_to_
+ f_return_status fl_seek_line_to(const f_dynamic_string buffer, f_string_location *location, const char seek_to_this) {
#ifndef _di_level_1_parameter_checking_
- if (position->start < 0) return f_error_set_error(f_invalid_parameter);
- if (position->stop < position->start) return f_error_set_error(f_invalid_parameter);
+ if (location == 0) return f_error_set_error(f_invalid_parameter);
+ if (location->start < 0) return f_error_set_error(f_invalid_parameter);
+ if (location->stop < location->start) return f_error_set_error(f_invalid_parameter);
if (buffer.used <= 0) return f_error_set_error(f_invalid_parameter);
- if (position->start >= buffer.used) return f_error_set_error(f_invalid_parameter);
+ if (location->start >= buffer.used) return f_error_set_error(f_invalid_parameter);
#endif // _di_level_1_parameter_checking_
- while (buffer.string[position->start] != seek_to_this) {
- if (buffer.string[position->start] == f_eol) return f_none;
+ while (buffer.string[location->start] != seek_to_this) {
+ if (buffer.string[location->start] == f_eol) return f_none_on_eol;
- ++position->start;
+ location->start++;
- if (position->start >= buffer.used) return f_none_on_eos;
- if (position->start > position->stop) return f_none_on_stop;
+ if (location->start >= buffer.used) return f_none_on_eos;
+ if (location->start > location->stop) return f_none_on_stop;
+ } // while
+
+ return f_none;
+ }
+#endif // _di_fl_seek_line_to_
+
+#ifndef _di_fl_seek_line_to_character_
+ f_return_status fl_seek_line_to_character(const f_dynamic_string buffer, f_string_location *location, const f_utf_character seek_to_this) {
+ #ifndef _di_level_1_parameter_checking_
+ if (location == 0) return f_error_set_error(f_invalid_parameter);
+ if (location->start < 0) return f_error_set_error(f_invalid_parameter);
+ if (location->stop < location->start) return f_error_set_error(f_invalid_parameter);
+ if (buffer.used <= 0) return f_error_set_error(f_invalid_parameter);
+ if (location->start >= buffer.used) return f_error_set_error(f_invalid_parameter);
+ #endif // _di_level_1_parameter_checking_
+
+ const f_u_short seek_width = f_macro_utf_character_width(seek_to_this);
+
+ f_status status = f_none;
+
+ f_u_short width = 0;
+
+ f_string_length max_width = 0;
+
+ while (location->start < buffer.used) {
+ max_width = (location->stop - location->start) + 1;
+
+ if (max_width > buffer.used - location->start) {
+ max_width = buffer.used - location->start;
+ }
+
+ width = f_macro_utf_byte_width(buffer.string[location->start]);
+
+ if (width == 1) {
+ if (buffer.string[location->start] == f_eol) return f_none_on_eol;
+
+ if (seek_width == width) {
+ if (buffer.string[location->start] == seek_to_this) return f_none;
+ }
+ }
+ else {
+ if (location->start + width >= buffer.used) return f_error_set_error(f_incomplete_utf_on_eos);
+ if (location->start + width > location->stop) return f_error_set_error(f_incomplete_utf_on_stop);
+
+ if (width == seek_width) {
+ f_utf_character character = 0;
+ status = f_utf_char_to_character(buffer.string + location->start, max_width, &character);
+
+ if (f_error_is_error(status)) {
+ return status;
+ }
+
+ if (character == seek_to_this) {
+ return f_none;
+ }
+ }
+ }
+
+ location->start += width;
+
+ if (location->start >= location->stop) return f_none_on_stop;
+ } // while
+
+ return f_none_on_eos;
+ }
+#endif // _di_fl_seek_line_to_character_
+
+#ifndef _di_fl_seek_to_
+ f_return_status fl_seek_to(const f_dynamic_string buffer, f_string_location *location, const char seek_to_this) {
+ #ifndef _di_level_1_parameter_checking_
+ if (location == 0) return f_error_set_error(f_invalid_parameter);
+ if (location->start < 0) return f_error_set_error(f_invalid_parameter);
+ if (location->stop < location->start) return f_error_set_error(f_invalid_parameter);
+ if (buffer.used <= 0) return f_error_set_error(f_invalid_parameter);
+ if (location->start >= buffer.used) return f_error_set_error(f_invalid_parameter);
+ #endif // _di_level_1_parameter_checking_
+
+ while (buffer.string[location->start] != seek_to_this) {
+ location->start++;
+
+ if (location->start >= buffer.used) return f_none_on_eos;
+ if (location->start > location->stop) return f_none_on_stop;
} // while
return f_none;
}
#endif // _di_fl_seek_to_
+#ifndef _di_fl_seek_to_character_
+ f_return_status fl_seek_to_character(const f_dynamic_string buffer, f_string_location *location, const f_utf_character seek_to_this) {
+ #ifndef _di_level_1_parameter_checking_
+ if (location == 0) return f_error_set_error(f_invalid_parameter);
+ if (location->start < 0) return f_error_set_error(f_invalid_parameter);
+ if (location->stop < location->start) return f_error_set_error(f_invalid_parameter);
+ if (buffer.used <= 0) return f_error_set_error(f_invalid_parameter);
+ if (location->start >= buffer.used) return f_error_set_error(f_invalid_parameter);
+ #endif // _di_level_1_parameter_checking_
+
+ const f_u_short seek_width = f_macro_utf_character_width(seek_to_this);
+
+ f_status status = f_none;
+
+ f_u_short width = 0;
+
+ f_string_length max_width = 0;
+
+ while (location->start < buffer.used) {
+ max_width = (location->stop - location->start) + 1;
+
+ if (max_width > buffer.used - location->start) {
+ max_width = buffer.used - location->start;
+ }
+
+ width = f_macro_utf_byte_width(buffer.string[location->start]);
+
+ if (width == 1) {
+ if (seek_width == width) {
+ if (buffer.string[location->start] == seek_to_this) return f_none;
+ }
+ }
+ else {
+ if (location->start + width >= buffer.used) return f_error_set_error(f_incomplete_utf_on_eos);
+ if (location->start + width > location->stop) return f_error_set_error(f_incomplete_utf_on_stop);
+
+ if (width == seek_width) {
+ f_utf_character character = 0;
+ status = f_utf_char_to_character(buffer.string + location->start, max_width, &character);
+
+ if (f_error_is_error(status)) {
+ return status;
+ }
+
+ if (character == seek_to_this) {
+ return f_none;
+ }
+ }
+ }
+
+ location->start += width;
+
+ if (location->start >= location->stop) return f_none_on_stop;
+ } // while
+
+ return f_none_on_eos;
+ }
+#endif // _di_fl_seek_to_character_
+
#ifndef _di_fl_compare_strings_
f_return_status fl_compare_strings(const f_string string1, const f_string string2, const f_string_length length1, const f_string_length length2) {
#ifndef _di_level_1_parameter_checking_
f_string_length i1 = 0;
f_string_length i2 = 0;
- f_string_length stop1 = length1;
- f_string_length stop2 = length2;
+ for (; i1 < length1 && i2 < length2; i1++, i2++) {
+ // skip past newlines in string1.
+ while (i1 < length1 && string1[i1] == f_eos) i1++;
+ if (i1 == length1) break;
- for (; i1 < stop1 && i2 < stop2; i1++, i2++) {
- while (i1 < stop1 && string1[i1] == f_eos) i1++;
- while (i2 < stop2 && string2[i2] == f_eos) i2++;
+ // skip past newlines in string2.
+ while (i2 < length2 && string2[i2] == f_eos) i2++;
+ if (i2 == length2) break;
if (string1[i1] != string2[i2]) return f_not_equal_to;
} // for
- while (i1 < stop1) {
+ // only return f_equal_to if all remaining characters are NULL.
+ while (i1 < length1) {
if (string1[i1] != f_eos) return f_not_equal_to;
i1++;
} // while
- while (i2 < stop2) {
+ while (i2 < length2) {
if (string2[i2] != f_eos) return f_not_equal_to;
i2++;
} // while
f_string_length i1 = 0;
f_string_length i2 = 0;
- f_string_length stop1 = string1.used;
- f_string_length stop2 = string2.used;
+ for (; i1 < string1.used && i2 < string2.used; i1++, i2++) {
+ // skip past newlines in string1.
+ while (i1 < string1.used && string1.string[i1] == f_eos) i1++;
+ if (i1 == string1.used) break;
- for (; i1 < stop1 && i2 < stop2; i1++, i2++) {
- while (i1 < stop1 && string1.string[i1] == f_eos) i1++;
- while (i2 < stop2 && string2.string[i2] == f_eos) i2++;
+ // skip past newlines in string2.
+ while (i2 < string2.used && string2.string[i2] == f_eos) i2++;
+ if (i2 == string2.used) break;
if (string1.string[i1] != string2.string[i2]) return f_not_equal_to;
} // for
- while (i1 < stop1) {
+ // only return f_equal_to if all remaining characters are NULL.
+ while (i1 < string1.used) {
if (string1.string[i1] != f_eos) return f_not_equal_to;
i1++;
} // while
- while (i2 < stop2) {
+ while (i2 < string2.used) {
if (string2.string[i2] != f_eos) return f_not_equal_to;
i2++;
} // while
#endif // _di_fl_compare_dynamic_strings_
#ifndef _di_fl_compare_partial_dynamic_strings_
- f_return_status fl_compare_partial_dynamic_strings(const f_dynamic_string string1, const f_dynamic_string string2, const f_string_location offset1, const f_string_location offset2) {
+ f_return_status fl_compare_dynamic_strings_partial(const f_dynamic_string string1, const f_dynamic_string string2, const f_string_location offset1, const f_string_location offset2) {
#ifndef _di_level_1_parameter_checking_
if (string1.used <= 0) return f_error_set_error(f_invalid_parameter);
if (string2.used <= 0) return f_error_set_error(f_invalid_parameter);
f_string_length i1 = offset1.start;
f_string_length i2 = offset2.start;
- f_string_length stop1 = offset1.stop + 1;
- f_string_length stop2 = offset2.stop + 1;
+ const f_string_length stop1 = offset1.stop + 1;
+ const f_string_length stop2 = offset2.stop + 1;
for (; i1 < stop1 && i2 < stop2; i1++, i2++) {
+ // skip past newlines in string1.
while (i1 < stop1 && string1.string[i1] == f_eos) i1++;
+ if (i1 == stop1) break;
+
+ // skip past newlines in string2.
while (i2 < stop2 && string2.string[i2] == f_eos) i2++;
+ if (i2 == stop2) break;
if (string1.string[i1] != string2.string[i2]) return f_not_equal_to;
} // for
+ // only return f_equal_to if all remaining characters are NULL.
while (i1 < stop1) {
if (string1.string[i1] != f_eos) return f_not_equal_to;
i1++;
extern "C" {
#endif
+/**
+ * Allocated a new string from the provided range in the buffer.
+ *
+ * @param buffer
+ * The buffer to rip from.
+ * @param location
+ * A range within the buffer representing the string to rip.
+ * @param result
+ * The new string, which will be allocated or reallocated as necessary.
+ *
+ * @return
+ * f_none on success.
+ * f_no_data if nothing to rip, no allocations or reallocations are performed.
+ * f_incomplete_utf_on_eos if end of sting is reached before a complete UTF-8 character can be processed.
+ * f_invalid_parameter (with error bit) if a parameter is invalid.
+ * f_allocation_error (with error bit) on memory allocation error.
+ * f_reallocation_error (with error bit) on memory reallocation error.
+ */
#ifndef _di_fl_rip_string_
- /**
- * given a start and stop position, this will return a new string based from the supplied buffer, based on the passed positions.
- * this will replace/overwrite existing information inside of the results variable.
- */
- extern f_return_status fl_rip_string(const f_dynamic_string buffer, const f_string_location position, f_dynamic_string *results);
+ extern f_return_status fl_rip_string(const f_dynamic_string buffer, const f_string_location location, f_dynamic_string *result);
#endif // _di_fl_rip_string_
-#ifndef _di_fl_seek_line_past_non_graph_
- /**
- * given a dynamic string and a string location, seek past all non-graph characters until a graph is reached.
- * will ignore the given placeholder.
- */
- extern f_return_status fl_seek_line_past_non_graph(const f_dynamic_string buffer, f_string_location *position, const char placeholder);
-#endif // _di_fl_seek_line_past_non_graph_
+/**
+ * Increment buffer location until a graph character (including UTF-8) or an EOL is matched.
+ *
+ * This will ignore the UTF-8 BOM.
+ *
+ * @param buffer
+ * The buffer to traverse.
+ * @param location
+ * A range within the buffer representing the start and stop locations.
+ * @param placeholder
+ * A single-width character representing a placeholder to ignore (may be NULL).
+ *
+ * @return
+ * f_none on success.
+ * f_none_on_eol on success, but stopped at EOL.
+ * f_none_on_eos on success, but stopped at end of buffer.
+ * f_incomplete_utf_on_stop (with error bit) if the stop location is reached before the complete UTF-8 character can be processed.
+ * f_incomplete_utf_on_eos (with error bit) if end of string is reached before a complete UTF-8 character can be processed.
+ * f_invalid_parameter (with error bit) if a parameter is invalid.
+ * f_allocation_error (with error bit) on memory allocation error.
+ * f_reallocation_error (with error bit) on memory reallocation error.
+ */
+#ifndef _di_fl_seek_line_until_graph_
+ extern f_return_status fl_seek_line_until_graph(const f_dynamic_string buffer, f_string_location *location, const char placeholder);
+#endif // _di_fl_seek_line_until_graph_
+/**
+ * Increment buffer location until a non-graph character (including UTF-8) or an EOL is matched.
+ *
+ * This will ignore the UTF-8 BOM.
+ *
+ * @param buffer
+ * The buffer to traverse.
+ * @param location
+ * A range within the buffer representing the start and stop locations.
+ * @param placeholder
+ * A single-width character representing a placeholder to ignore (may be NULL).
+ *
+ * @return
+ * f_none on success.
+ * f_none_on_eol on success, but stopped at EOL.
+ * f_none_on_eos on success, but stopped at end of buffer.
+ * f_none_on_stop on success, but stopped stop location.
+ * f_incomplete_utf_on_stop (with error bit) if the stop location is reached before the complete UTF-8 character can be processed.
+ * f_incomplete_utf_on_eos (with error bit) if end of string is reached before a complete UTF-8 character can be processed.
+ * f_invalid_parameter (with error bit) if a parameter is invalid.
+ * f_allocation_error (with error bit) on memory allocation error.
+ * f_reallocation_error (with error bit) on memory reallocation error.
+ */
#ifndef _di_fl_seek_line_until_non_graph_
- /**
- * given a dynamic string and a string location, seek past all graph characters until a non-graph is reached.
- * will ignore the given placeholder.
- */
- extern f_return_status fl_seek_line_until_non_graph(const f_dynamic_string buffer, f_string_location *position, const char placeholder);
+ extern f_return_status fl_seek_line_until_non_graph(const f_dynamic_string buffer, f_string_location *location, const char placeholder);
#endif // _di_fl_seek_line_until_non_graph_
+/**
+ * Seek the buffer location forward until the character (1-byte wide) or EOL is reached.
+ *
+ * @param buffer
+ * The buffer to traverse.
+ * @param location
+ * A range within the buffer representing the start and stop locations.
+ * The start location will be incremented by seek.
+ * @param seek_to_this
+ * A single-width character representing a character to seek to.
+ *
+ * @return
+ * f_none on success.
+ * f_none_on_eol on success, but stopped at EOL.
+ * f_none_on_eos on success, but stopped at end of buffer.
+ * f_none_on_stop on success, but stopped stop location.
+ * f_invalid_parameter (with error bit) if a parameter is invalid.
+ *
+ * @see: fl_seek_line_to_character()
+ */
+#ifndef _di_fl_seek_line_to_
+ extern f_return_status fl_seek_line_to(const f_dynamic_string buffer, f_string_location *location, const char seek_to_this);
+#endif // _di_fl_seek_line_to_
+
+/**
+ * Seek the buffer location forward until the character (up to 4-byte wide) or EOL is reached.
+ *
+ * @param buffer
+ * The buffer to traverse.
+ * @param location
+ * A range within the buffer representing the start and stop locations.
+ * The start location will be incremented by seek.
+ * @param seek_to_this
+ * A 1-width, 2-width, 3-width, or 4-width character representing a character to seek to.
+ *
+ * @return
+ * f_none on success.
+ * f_none_on_eol on success, but stopped at EOL.
+ * f_none_on_eos on success, but stopped at end of buffer.
+ * f_incomplete_utf_on_stop (with error bit) if the stop location is reached before the complete UTF-8 character can be processed.
+ * f_incomplete_utf_on_eos (with error bit) if end of string is reached before a complete UTF-8 character can be processed.
+ * f_invalid_parameter (with error bit) if a parameter is invalid.
+ *
+ * @see: fl_seek_line_to()
+ */
+#ifndef _di_fl_seek_line_to_character_
+ extern f_return_status fl_seek_line_to_character(const f_dynamic_string buffer, f_string_location *location, const f_utf_character seek_to_this);
+#endif // _di_fl_seek_line_to_character_
+
+/**
+ * Seek the buffer location forward until the character (1-byte wide) is reached.
+ *
+ * @param buffer
+ * The buffer to traverse.
+ * @param location
+ * A range within the buffer representing the start and stop locations.
+ * The start location will be incremented by seek.
+ * @param seek_to_this
+ * A single-width character representing a character to seek to.
+ *
+ * @return
+ * f_none on success.
+ * f_none_on_eos on success, but stopped at end of buffer.
+ * f_none_on_stop on success, but stopped stop location.
+ * f_incomplete_utf_on_stop (with error bit) if the stop location is reached before the complete UTF-8 character can be processed.
+ * f_incomplete_utf_on_eos (with error bit) if end of string is reached before a complete UTF-8 character can be processed.
+ * f_invalid_parameter (with error bit) if a parameter is invalid.
+ *
+ * @see: fl_seek_to_character()
+ */
#ifndef _di_fl_seek_to_
- /**
- * given a dynamic string and a string location, seek past all characters until the given character is reached.
- */
- extern f_return_status fl_seek_to(const f_dynamic_string buffer, f_string_location *position, const char seek_to_this);
+ extern f_return_status fl_seek_to(const f_dynamic_string buffer, f_string_location *location, const char seek_to_this);
#endif // _di_fl_seek_to_
+/**
+ * Seek the buffer location forward until the character (up to 4-byte wide) is reached.
+ *
+ * @param buffer
+ * The buffer to traverse.
+ * @param location
+ * A range within the buffer representing the start and stop locations.
+ * The start location will be incremented by seek.
+ * @param seek_to_this
+ * A 1-width, 2-width, 3-width, or 4-width character representing a character to seek to.
+ *
+ * @return
+ * f_none on success.
+ * f_none_on_eos on success, but stopped at end of buffer.
+ * f_incomplete_utf_on_stop (with error bit) if the stop location is reached before the complete UTF-8 character can be processed.
+ * f_incomplete_utf_on_eos (with error bit) if end of string is reached before a complete UTF-8 character can be processed.
+ * f_invalid_parameter (with error bit) if a parameter is invalid.
+ *
+ * @see: fl_seek_to()
+ */
+#ifndef _di_fl_seek_to_character_
+ extern f_return_status fl_seek_to_character(const f_dynamic_string buffer, f_string_location *location, const f_utf_character seek_to_this);
+#endif // _di_fl_seek_to_character_
+
+/**
+ * Compare two strings, similar to strncmp().
+ *
+ * This does not stop on NULL.
+ * NULL characters are ignored.
+ *
+ * @param string1
+ * String to compare.
+ * @param string2
+ * String to compare.
+ * @param length1
+ * Length of string1.
+ * @param length2
+ * Length of string2.
+ *
+ * @return
+ * f_equal_to when both strings equal.
+ * f_not_equal_to when both strings do not equal.
+ * f_invalid_parameter (with error bit) if a parameter is invalid.
+ *
+ * @see: fl_compare_dynamic_strings()
+ * @see: fl_compare_dynamic_strings_partial()
+ */
#ifndef _di_fl_compare_strings_
- /**
- * this compares two strings and works similar to that of strncmp(..) but has significant differences to strncmp(..).
- * given two strings, this will return either f_equal_to or f_not_equal_to.
- * this does not stop on f_eos and f_eos will be ignored as if it were not taking up any space, therefor a 5 character string could return f_equal_to if the 5 character string contains an f_eos anywhere within it.
- */
extern f_return_status fl_compare_strings(const f_string string1, const f_string string2, const f_string_length length1, const f_string_length length2);
#endif // _di_fl_compare_strings_
+/**
+ * Compare two strings, similar to strncmp().
+ *
+ * This does not stop on NULL.
+ * NULL characters are ignored.
+ *
+ * @param string1
+ * String to compare.
+ * @param string2
+ * String to compare.
+ *
+ * @return
+ * f_equal_to when both strings equal.
+ * f_not_equal_to when both strings do not equal.
+ * f_invalid_parameter (with error bit) if a parameter is invalid.
+ *
+ * @see: fl_compare_strings()
+ * @see: fl_compare_dynamic_strings_partial()
+ */
#ifndef _di_fl_compare_dynamic_strings_
- /**
- * this compares two dynamic strings and works similar to that of strncmp(..) but has significant differences to strncmp(..).
- * given two strings, this will return either f_equal_to or f_not_equal_to.
- * this is far safer than fl_compare_strings(..) as dynamic string contain size information within them.
- * this does not stop on f_eos and f_eos will be ignored as if it were not taking up any space, therefor a 5 character string could return f_equal_to if the 5 character string contains an f_eos anywhere within it.
- */
extern f_return_status fl_compare_dynamic_strings(const f_dynamic_string string1, const f_dynamic_string string2);
#endif // _di_fl_compare_dynamic_strings_
+/**
+ * Compare two strings, similar to strncmp(), but restricted to the given ranges.
+ *
+ * This does not stop on NULL.
+ * NULL characters are ignored.
+ *
+ * @param string1
+ * String to compare.
+ * @param string2
+ * String to compare.
+ * @param offset1
+ * A range within the string1 to restrict the comparison to.
+ * @param offset2
+ * A range within the string2 to restrict the comparison to.
+ *
+ * @return
+ * f_equal_to when both strings equal.
+ * f_not_equal_to when both strings do not equal.
+ * f_invalid_parameter (with error bit) if a parameter is invalid.
+ *
+ * @see: fl_compare_strings()
+ * @see: fl_compare_dynamic_strings()
+ */
#ifndef _di_fl_compare_partial_dynamic_strings_
- /**
- * this functions identical to fl_compare_dynamic_strings, but uses offsets for both strings.
- */
- extern f_return_status fl_compare_partial_dynamic_strings(const f_dynamic_string string1, const f_dynamic_string string2, const f_string_location offset1, const f_string_location offset2);
+ extern f_return_status fl_compare_dynamic_strings_partial(const f_dynamic_string string1, const f_dynamic_string string2, const f_string_location offset1, const f_string_location offset2);
#endif // _di_fl_compare_partial_dynamic_strings_
#ifdef __cplusplus
location.stop = firewall_group_main_length - 1;
fixed_string.string = firewall_group_main;
fixed_string.used = firewall_group_main_length;
- if (fl_compare_partial_dynamic_strings(local->buffer, fixed_string, local->chain_objects.array[i], location) == f_equal_to) {
+ if (fl_compare_dynamic_strings_partial(local->buffer, fixed_string, local->chain_objects.array[i], location) == f_equal_to) {
new_chain = f_false;
reserved->has_main = f_true;
reserved->main_at = i;
location.stop = firewall_group_stop_length - 1;
fixed_string.string = firewall_group_stop;
fixed_string.used = firewall_group_stop_length;
- if (fl_compare_partial_dynamic_strings(local->buffer, fixed_string, local->chain_objects.array[i], location) == f_equal_to) {
+ if (fl_compare_dynamic_strings_partial(local->buffer, fixed_string, local->chain_objects.array[i], location) == f_equal_to) {
new_chain = f_false;
reserved->has_stop = f_true;
reserved->stop_at = i;
location.stop = firewall_group_lock_length - 1;
fixed_string.string = firewall_group_lock;
fixed_string.used = firewall_group_lock_length;
- if (fl_compare_partial_dynamic_strings(local->buffer, fixed_string, local->chain_objects.array[i], location) == f_equal_to) {
+ if (fl_compare_dynamic_strings_partial(local->buffer, fixed_string, local->chain_objects.array[i], location) == f_equal_to) {
new_chain = f_false;
reserved->has_lock = f_true;
reserved->lock_at = i;
location.stop = firewall_group_lock_length - 1;
fixed_string.string = firewall_chain_none;
fixed_string.used = firewall_chain_none_length;
- if (fl_compare_partial_dynamic_strings(local->buffer, fixed_string, local->chain_objects.array[i], location) == f_equal_to) {
+ if (fl_compare_dynamic_strings_partial(local->buffer, fixed_string, local->chain_objects.array[i], location) == f_equal_to) {
new_chain = f_false;
}
location.start = 0;
location.stop = data->chains.array[j].used - 1;
- if (fl_compare_partial_dynamic_strings(local->buffer, data->chains.array[j], local->chain_objects.array[i], location) == f_equal_to) {
+ if (fl_compare_dynamic_strings_partial(local->buffer, data->chains.array[j], local->chain_objects.array[i], location) == f_equal_to) {
new_chain = f_false;
local->chain_ids.array[i] = j;
f_print
f_strings
f_types
+f_utf
fl_colors
fl_console
fl_directory
// sit and wait for signals.
- while (1) {
+ for (;;) {
signal_result = sigwaitinfo(&signal_mask, &signal_information);
if (signal_result < 0) {
memset(&signal_information, 0, sizeof(siginfo_t));
continue;
- }
+ } // for
}
init_delete_argument((*argument));
f_print
f_strings
f_types
+f_utf
fl_colors
fl_console
fl_directory
projects / fll / commitdiff