add projbase to repo

1 files changed, 703 insertions, 0 deletions

diff --git a/project-base/src/string_utils.c b/project-base/src/string_utils.c
new file mode 100644
index 0000000..54395e1
--- /dev/null
+++ b/project-base/src/string_utils.c
@@ -0,0 +1,703 @@
+/* 
+*  BSD 2-Clause “Simplified” License
+*  Copyright (c) 2019, Aldrik Ramaekers, aldrik.ramaekers@protonmail.com
+*  All rights reserved.
+*/
+
+char *string_get_next(char *list, char *buffer, char seperator)
+{
+	char *orig = list;
+	
+	utf8_int32_t ch;
+	while((list = utf8codepoint(list, &ch)) && ch != seperator && ch)
+	{
+		list++;
+	}
+	
+	char len = list - orig;
+	
+	string_copyn(buffer, orig, len);
+	return list;
+}
+
+bool string_match(char *first, char *second)
+{
+	// If we reach at the end of both strings, we are done 
+	if (*first == '\0' && *second == '\0') 
+		return true; 
+	
+	// Make sure that the characters after '*' are present 
+	// in second string. This function assumes that the first 
+	// string will not contain two consecutive '*' 
+	if (*first == '*' && *(first+1) != '\0' && *second == '\0') 
+		return false;
+	
+	// If the first string contains '?', or current characters 
+	// of both strings string_match
+	if (*first == '?' || *first == *second) 
+		return string_match(first+1, second+1);
+	
+	// If there is *, then there are two possibilities 
+	// a) We consider current character of second string 
+	// b) We ignore current character of second string. 
+	if (*first == '*') 
+		return string_match(first+1, second) || string_match(first, second+1); 
+	return false; 
+}
+
+bool string_is_whitespace(char *text) {
+	utf8_int32_t ch;
+	while((text = utf8codepoint(text, &ch)) && ch)
+	{
+		if (ch != ' ') return false;
+	}
+	return true;
+}
+
+bool string_is_asteriks(char *text)
+{
+	utf8_int32_t ch;
+	if (!utf8len(text)) return false;
+	while((text = utf8codepoint(text, &ch)) && ch)
+	{
+		if (ch != '*') return false;
+	}
+	return true;
+}
+
+bool string_contains_ex(char *text_to_search, char *text_to_find, array *text_matches, bool *cancel_search)
+{
+	bool final_result = false;
+	bool is_asteriks_only = false;
+
+#if 0
+	int len = strlen(text_to_find)+1;
+	char *tmp = mem_alloc(len);
+	strcpy(tmp, text_to_find);
+	text_to_find = tmp;
+	#endif
+
+	// * wildcard at the start of text to find is not needed
+	if (string_is_asteriks(text_to_find))
+	{
+		is_asteriks_only = true;
+		text_to_find += strlen(text_to_find);
+	}
+	
+	// remove all asteriks from start
+	utf8_int32_t br;
+	while(utf8codepoint(text_to_find, &br) && br == '*')
+	{
+		text_to_find = utf8codepoint(text_to_find, &br);
+	}
+	
+	char *text_to_find_original = text_to_find;
+	bool save_info = (text_matches != 0);
+	
+	utf8_int32_t text_to_search_ch = 0;
+	utf8_int32_t text_to_find_ch = 0;
+	
+	s32 line_nr_val = 1;
+	s32 word_offset_val = 0;
+	s32 word_match_len_val = 0;
+	char* line_start_ptr = text_to_search;
+	
+	s32 index = 0;
+	while((text_to_search = utf8codepoint(text_to_search, &text_to_search_ch))
+		  && text_to_search_ch)
+	{
+		if (cancel_search && *cancel_search) goto set_info_and_return_failure;
+		word_offset_val++;
+		if (text_to_search_ch == '\n') 
+		{
+			line_nr_val++;
+			word_offset_val = 0;
+			line_start_ptr = text_to_search;
+		}
+		
+		char *text_to_search_current_attempt = text_to_search;
+		utf8_int32_t text_to_search_current_attempt_ch = text_to_search_ch;
+		
+		bool in_wildcard = false;
+		
+		text_to_find = utf8codepoint(text_to_find, &text_to_find_ch);
+		//text_to_search_current_attempt = utf8codepoint(text_to_search_current_attempt,
+		//&text_to_search_current_attempt_ch);
+		
+		word_match_len_val = 0;
+		while(text_to_search_current_attempt_ch)
+		{
+			if (cancel_search && *cancel_search) goto set_info_and_return_failure;
+			
+			// wildcard, accept any character in text to search
+			if (text_to_find_ch == '?')
+				goto continue_search;
+			
+			// character matches, 
+			if (text_to_find_ch == text_to_search_current_attempt_ch && in_wildcard)
+				in_wildcard = false;
+			
+			// wildcard, accept any characters in text to search untill next char is found
+			if (text_to_find_ch == '*')
+			{
+				text_to_find = utf8codepoint(text_to_find, &text_to_find_ch);
+				in_wildcard = true;
+			}
+			
+			// text to find has reached 0byte, word has been found
+			if (text_to_find_ch == 0 || string_is_asteriks(text_to_find))
+			{
+				done:
+				if (save_info)
+				{
+					text_match new_match;
+					new_match.line_nr = line_nr_val;
+					new_match.word_offset = word_offset_val-1;
+					new_match.word_match_len = word_match_len_val;
+					new_match.line_start = line_start_ptr;
+					new_match.line_info = 0;
+					array_push(text_matches, (uint8_t *)&new_match);
+				}
+				
+				final_result = true;
+				
+				if (is_asteriks_only)
+				{
+					return final_result;
+				}
+				
+				break;
+			}
+			
+			// character does not match, continue search
+			if (text_to_find_ch != text_to_search_current_attempt_ch && !in_wildcard)
+				break;
+			
+			continue_search:
+			if (!in_wildcard)
+				text_to_find = utf8codepoint(text_to_find, &text_to_find_ch);
+			
+			text_to_search_current_attempt = utf8codepoint(
+				text_to_search_current_attempt,
+				&text_to_search_current_attempt_ch);
+			
+			//if (!text_to_search_current_attempt_ch && string_is_asteriks(text_to_find)) goto done;
+			if (!text_to_search_current_attempt_ch && !text_to_find_ch) goto done;
+			
+			word_match_len_val++;
+		}
+		
+		text_to_find = text_to_find_original;
+		index++;
+	}
+	
+	return final_result;
+	
+	set_info_and_return_failure:
+	return false;
+}
+
+static char *ltrim(char *str, const char *seps)
+{
+	size_t totrim;
+	if (seps == NULL) {
+		seps = "\t\n\v\f\r ";
+	}
+	totrim = strspn(str, seps);
+	if (totrim > 0) {
+		size_t len = strlen(str);
+		if (totrim == len) {
+			str[0] = '\0';
+		}
+		else {
+			memmove(str, str + totrim, len + 1 - totrim);
+		}
+	}
+	return str;
+}
+
+static char *rtrim(char *str, const char *seps)
+{
+	int i;
+	if (seps == NULL) {
+		seps = "\t\n\v\f\r ";
+	}
+	i = strlen(str) - 1;
+	while (i >= 0 && strchr(seps, str[i]) != NULL) {
+		str[i] = '\0';
+		i--;
+	}
+	return str;
+}
+
+inline void string_trim(char *string)
+{
+	ltrim(rtrim(string, 0), 0);
+}
+
+inline bool string_equals(char *first, char *second)
+{
+	return (strcmp(first, second) == 0);
+}
+
+s32 string_length(char *str)
+{
+	utf8_int32_t ch = 0;
+	s32 i = 0;
+	while((str = utf8codepoint(str, &ch)) && ch)
+	{
+		i++;
+	}
+	return i;
+}
+
+// replaces " with \" for file formats
+void string_appendf(char *buffer, char *text)
+{
+	u32 len = strlen(buffer);
+	while(*text)
+	{
+		if (*text < 32)
+		{
+			buffer[len] = ' ';
+			len++;
+			text++;
+			continue;
+		}
+		
+		if (*text == '"')
+		{
+			buffer[len] = '\\';
+			len++;
+		}
+		if (*text == '\\')
+		{
+			buffer[len] = '\\';
+			len++;
+		}
+		
+		buffer[len] = *text;
+		len++;
+		text++;
+	}
+}
+
+void string_copyn(char *buffer, char *text, s32 bufferlen)
+{
+	u32 len = 0;
+	while(*text && len < bufferlen)
+	{
+		buffer[len] = *text;
+		len++;
+		text++;
+	}
+	buffer[len] = 0;
+}
+
+void string_appendn(char *buffer, char *text, s32 bufferlen)
+{
+	u32 len = strlen(buffer);
+	while(*text && len < bufferlen)
+	{
+		buffer[len] = *text;
+		len++;
+		text++;
+	}
+	buffer[len] = 0;
+}
+
+void string_append(char *buffer, char *text)
+{
+	u32 len = strlen(buffer);
+	while(*text)
+	{
+		buffer[len] = *text;
+		len++;
+		text++;
+	}
+	buffer[len] = 0;
+}
+
+bool string_remove(char **buffer, char *text)
+{
+	s32 len = strlen(text);
+	char tmp[200];
+	memcpy(tmp, *buffer, len);
+	memset(tmp+len, 0, 1);
+	
+	if (string_equals(tmp, text))
+	{
+		*buffer += len;
+		return true;
+	}
+	
+	return false;
+}
+
+char* string_get_json_literal(char **buffer, char *tmp)
+{
+	char *buf_start = *buffer;
+	char *buf = *buffer;
+	s32 len = 0;
+	while(*buf)
+	{
+		if ((*buf == ',' || *buf == '}') && (len > 0 && *(buf-1) == '"') && (len > 1 && *(buf-2) != '\\'))
+		{
+			memcpy(tmp, buf_start, len);
+			memset(tmp+len-1, 0, 1);
+			*buffer += len-1;
+			return tmp;
+		}
+		
+		len++;
+		buf++;
+	}
+	
+	return tmp;
+}
+
+s32 string_get_json_ulong_number(char **buffer)
+{
+	char tmp[20];
+	char *buf_start = *buffer;
+	char *buf = *buffer;
+	s32 len = 0;
+	while(*buf)
+	{
+		if (*buf == ',' || *buf == '}')
+		{
+			memcpy(tmp, buf_start, len);
+			memset(tmp+len, 0, 1);
+			*buffer += len;
+			return string_to_u64(tmp);
+		}
+		
+		len++;
+		buf++;
+	}
+	
+	return 0;
+}
+
+s32 string_get_json_number(char **buffer)
+{
+	char tmp[20];
+	char *buf_start = *buffer;
+	char *buf = *buffer;
+	s32 len = 0;
+	while(*buf)
+	{
+		if (*buf == ',' || *buf == '}')
+		{
+			memcpy(tmp, buf_start, len);
+			memset(tmp+len, 0, 1);
+			*buffer += len;
+			return string_to_s32(tmp);
+		}
+		
+		len++;
+		buf++;
+	}
+	
+	return 0;
+}
+
+void utf8_str_remove_range(char *str, s32 from, s32 to)
+{
+	char *orig_str = str;
+	s32 i = 0;
+	utf8_int32_t ch = 0;
+	s32 total_len = strlen(str)+1+4;
+	char *replacement = calloc(total_len,1);
+	char *rep_off = replacement;
+	replacement[0] = 0;
+	
+	while((str = utf8codepoint(str, &ch)) && ch)
+	{
+		if (i < from || i >= to)
+		{
+			rep_off = utf8catcodepoint(rep_off, ch, 5);
+		}
+		
+		++i;
+	}
+	*rep_off = 0;
+	
+	string_copyn(orig_str, replacement, MAX_INPUT_LENGTH);
+	mem_free(replacement);
+}
+
+void utf8_str_remove_at(char *str, s32 at)
+{
+	char *orig_str = str;
+	s32 i = 0;
+	utf8_int32_t ch = 0;
+	s32 total_len = strlen(str)+1+4;
+	char *replacement = calloc(total_len,1);
+	char *rep_off = replacement;
+	replacement[0] = 0;
+	
+	while((str = utf8codepoint(str, &ch)) && ch)
+	{
+		if (at != i)
+		{
+			rep_off = utf8catcodepoint(rep_off, ch, 5);
+		}
+		
+		++i;
+	}
+	*rep_off = 0;
+	
+	string_copyn(orig_str, replacement, MAX_INPUT_LENGTH);
+	mem_free(replacement);
+}
+
+void utf8_str_insert_utf8str(char *str, s32 at, char *toinsert)
+{
+	s32 index = 0;
+	utf8_int32_t ch;
+	while((toinsert = utf8codepoint(toinsert, &ch)) && ch)
+	{
+		utf8_str_insert_at(str, at+index, ch);
+		index++;
+	}
+}
+
+void utf8_str_insert_at(char *str, s32 at, utf8_int32_t newval)
+{
+	char *orig_str = str;
+	s32 i = 0;
+	utf8_int32_t ch = 0;
+	s32 total_len = strlen(str)+1+4;
+	char *replacement = calloc(total_len,1);
+	char *rep_off = replacement;
+	replacement[0] = 0;
+	
+	while((str = utf8codepoint(str, &ch)))
+	{
+		if (at == i)
+		{
+			rep_off = utf8catcodepoint(rep_off, newval, 5);
+		}
+		
+		rep_off = utf8catcodepoint(rep_off, ch, 5);
+		
+		++i;
+		
+		if (!ch) break;
+	}
+	*rep_off = 0;
+	
+	string_copyn(orig_str, replacement, MAX_INPUT_LENGTH);
+	mem_free(replacement);
+}
+
+char *utf8_str_copy_upto(char *str, s32 roof, char *buffer)
+{
+	utf8_int32_t ch = 0;
+	s32 index = 0;
+	char *orig_buffer = buffer;
+	while((str = utf8codepoint(str, &ch)) && ch)
+	{
+		if (index == roof) break;
+		buffer = utf8catcodepoint(buffer, ch, 5);
+		index++;
+	}
+	buffer = utf8catcodepoint(buffer, 0, 5);
+	
+	return orig_buffer;
+}
+
+char *utf8_str_copy_range(char *str, s32 floor, s32 roof, char *buffer)
+{
+	utf8_int32_t ch = 0;
+	s32 index = 0;
+	char *orig_buffer = buffer;
+	while((str = utf8codepoint(str, &ch)) && ch)
+	{
+		if (index == roof) break;
+		if (index >= floor)
+			buffer = utf8catcodepoint(buffer, ch, 5);
+		index++;
+	}
+	buffer = utf8catcodepoint(buffer, 0, 5);
+	
+	return orig_buffer;
+}
+
+void utf8_str_replace_at(char *str, s32 at, utf8_int32_t newval)
+{
+	char *orig_str = str;
+	s32 i = 0;
+	utf8_int32_t ch = 0;
+	s32 total_len = strlen(str)+1+4;
+	char *replacement = calloc(total_len,1);
+	char *rep_off = replacement;
+	replacement[0] = 0;
+	
+	while((str = utf8codepoint(str, &ch)) && ch)
+	{
+		if (at == i)
+		{
+			rep_off = utf8catcodepoint(rep_off, newval, 5);
+		}
+		else
+		{
+			rep_off = utf8catcodepoint(rep_off, ch, 5);
+		}
+		++i;
+	}
+	*rep_off = 0;
+	
+	string_copyn(orig_str, replacement, MAX_INPUT_LENGTH);
+	mem_free(replacement);
+}
+
+char* utf8_str_upto(char *str, s32 index)
+{
+	s32 i = 0;
+	utf8_int32_t ch;
+	char *prev_str = str;
+	while((str = utf8codepoint(str, &ch)) && ch)
+	{
+		if (index == i) return prev_str;
+		prev_str = str;
+		++i;
+	}
+	
+	return str;
+}
+
+utf8_int32_t utf8_str_at(char *str, s32 index)
+{
+	s32 i = 0;
+	utf8_int32_t ch;
+	while((str = utf8codepoint(str, &ch)) && ch)
+	{
+		if (index == i) return ch;
+		
+		++i;
+	}
+	
+	return 0;
+}
+
+bool string_is_numeric(char *str)
+{
+	utf8_int32_t ch;
+	while((str = utf8codepoint(str, &ch)) && ch)
+	{
+		if (!(ch >= 48 && ch <= 57))
+		{
+			return false;
+		}
+	}
+	
+	return true;
+}
+
+void string_convert_crlf_to_lf(char *buffer)
+{
+	char *buffer_original = buffer;
+	
+	int write_offset = 0;
+	int read_offset = 0;
+	
+	while(buffer[read_offset])
+	{
+		if (buffer[read_offset] != 0x0D)
+		{
+			buffer_original[write_offset] = buffer[read_offset];
+			
+			++write_offset;
+		}
+		
+		++read_offset;
+	}
+}
+
+inline u64 string_to_u64(char *str)
+{
+	return (u64)strtoull(str, 0, 10);
+}
+
+inline u32 string_to_u32(char *str)
+{
+	return (u32)strtoul(str, 0, 10);
+}
+
+inline u16 string_to_u16(char *str)
+{
+	return (u16)strtoul(str, 0, 10);
+}
+
+inline u8 string_to_u8(char *str)
+{
+	return (u8)strtoul(str, 0, 10);
+}
+
+inline s64 string_to_s64(char *str)
+{
+	return (s64)strtoll(str, 0, 10);
+}
+
+inline s32 string_to_s32(char *str)
+{
+	return (u32)strtol(str, 0, 10);
+}
+
+inline s16 string_to_s16(char *str)
+{
+	return (s16)strtol(str, 0, 10);
+}
+
+inline s8 string_to_s8(char *str)
+{
+	return (s8)strtol(str, 0, 10);
+}
+
+inline f32 string_to_f32(char *str)
+{
+	return (f32)atof(str);
+}
+
+inline f64 string_to_f64(char *str)
+{
+	return (f64)strtod(str, NULL);
+}
+
+array string_split(char *text)
+{	
+	array result = array_create(MAX_INPUT_LENGTH);
+	
+	char current_filter[MAX_INPUT_LENGTH];
+	s32 filter_len = 0;
+	while(*text)
+	{
+		char ch = *text;
+		
+		if (ch == ',')
+		{
+			current_filter[filter_len] = 0;
+			array_push(&result, (uint8_t*)current_filter);
+			filter_len = 0;
+		}
+		else
+		{
+			if(filter_len < MAX_INPUT_LENGTH-1)
+			{
+				current_filter[filter_len++] = ch;
+			}
+			else
+			{
+				current_filter[filter_len] = ch;
+			}
+		}
+		
+		text++;
+	}
+	current_filter[filter_len] = 0;
+	array_push(&result, (uint8_t*)current_filter);
+	
+	return result;
+}