VuoText implementation.
Definition in file VuoText.c.
Go to the source code of this file.
Macros | |
| #define | UTF8_ACCEPT 0 |
| VuoText_isValidUtf8 is based on code by Bjoern Hoehrmann. More... | |
| #define | UTF8_REJECT 1 |
| the byte is not allowed to occur at its position More... | |
Functions | |
| VuoText | VuoText_makeFromJson (json_object *js) |
| json_object * | VuoText_getJson (const VuoText value) |
| VuoText | VuoText_truncateWithEllipsis (const VuoText subject, int maxLength, VuoTextTruncation where) |
If subject is less than or equal to maxLength Unicode characters long, returns subject. More... | |
| char * | VuoText_getSummary (const VuoText value) |
| VuoText | VuoText_make (const char *unquotedString) |
| VuoText | VuoText_makeWithMaxLength (const void *data, const size_t maxLength) |
| Creates a VuoText value from an untrusted source (one that might not contain a NULL terminator within its memory page). More... | |
| VuoText | VuoText_makeFromCFString (const void *cfs) |
Creates a VuoText value from a CFStringRef. More... | |
| static bool | VuoText_isValidUtf8 (const unsigned char *data, unsigned long size) |
Returns true if data is valid UTF-8 text. More... | |
| VuoText | VuoText_makeFromData (const unsigned char *data, const unsigned long size) |
Attempts to interpret data as UTF-8 text. More... | |
| VuoText | VuoText_makeFromUtf32 (const uint32_t *data, size_t size) |
| Create a new VuoText string from an array of UTF-32 values. More... | |
| VuoText | VuoText_makeFromMacRoman (const char *string) |
| Creates a new VuoText from a MacRoman-encoded string. More... | |
| size_t | VuoText_length (const VuoText text) |
| size_t | VuoText_byteCount (const VuoText text) |
| Returns the number of bytes in the text, not including the null terminator. More... | |
| bool | VuoText_isEmpty (const VuoText text) |
Returns true if text is empty (is NULL or is non-NULL with zero length). More... | |
| bool | VuoText_isPopulated (const VuoText text) |
Returns true if text is not empty. More... | |
| bool | VuoText_areEqual (const VuoText text1, const VuoText text2) |
| Returns true if the two texts represent the same Unicode string (even if they use different UTF-8 encodings or Unicode character decompositions). More... | |
| static bool | isLessThan (const VuoText text1, const VuoText text2, CFStringCompareFlags flags) |
Helper for VuoText_isLessThan*(). More... | |
| bool | VuoText_isLessThan (const VuoText text1, const VuoText text2) |
| bool | VuoText_isLessThanCaseInsensitive (const VuoText text1, const VuoText text2) |
| bool | VuoText_isLessThanNumeric (const VuoText text1, const VuoText text2) |
| bool | VuoText_compare (VuoText text1, VuoTextComparison comparison, VuoText text2) |
| size_t | VuoText_findFirstOccurrence (const VuoText string, const VuoText substring, const size_t startIndex) |
| size_t | VuoText_findLastOccurrence (const VuoText string, const VuoText substring) |
| VuoList_VuoInteger | VuoText_findOccurrences (const VuoText string, const VuoText substring) |
Returns a list containing all occurrences of substring in string. More... | |
| VuoText | VuoText_substring (const VuoText string, int startIndex, int length) |
| VuoText | VuoText_append (VuoText *texts, size_t textsCount) |
| VuoText * | VuoText_split (VuoText text, VuoText separator, bool includeEmptyParts, size_t *partsCount) |
| VuoText | VuoText_replace (VuoText subject, VuoText stringToFind, VuoText replacement) |
Returns a new string in which each occurrence of stringToFind in subject has been replaced with replacement. More... | |
| VuoText | VuoText_insert (const VuoText string, int startIndex, const VuoText newText) |
Returns a new string with newText inserted at the startIndex. More... | |
| VuoText | VuoText_removeAt (const VuoText string, int startIndex, int length) |
Returns a new string where characters from startIndex to startIndex + length are removed. More... | |
| char * | VuoText_format (const char *format,...) |
Returns a new string formatted using the printf-style format string. More... | |
| VuoText | VuoText_trim (const VuoText text) |
Returns a new string consisting of text without the whitespace at the beginning and end. More... | |
| static bool | VuoText_isASCII7 (VuoText text) |
Returns true if all byte values in text are between 0 and 127. More... | |
| VuoText | VuoText_changeCase (const VuoText text, VuoTextCase textCase) |
Returns a new string with the text characters cased in the textCase style. More... | |
| uint32_t * | VuoText_getUtf32Values (const VuoText text, size_t *length) |
| Returns an array of unicode 32 bit decimal values for each character in a string. More... | |
Variables | |
| static const uint8_t | utf8d [] |
| The first part maps bytes to character classes, the second part encodes a deterministic finite automaton using these character classes as transitions. More... | |
| #define UTF8_ACCEPT 0 |
VuoText_isValidUtf8 is based on code by Bjoern Hoehrmann.
Copyright (c) 2008-2009 Bjoern Hoehrmann bjoern@hoehrmann.de See https://web.archive.org/web/20190528032751/http://bjoern.hoehrmann.de/utf-8/decoder/dfa/ for details.
Permission is hereby granted, free of charge, to any person obtaining a copy of this software and associated documentation files (the "Software"), to deal in the Software without restriction, including without limitation the rights to use, copy, modify, merge, publish, distribute, sublicense, and/or sell copies of the Software, and to permit persons to whom the Software is furnished to do so, subject to the following conditions:
The above copyright notice and this permission notice shall be included in all copies or substantial portions of the Software.
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE. enough bytes have been read for a character
| #define UTF8_REJECT 1 |
|
static |
|
static |
|
static |
The first part maps bytes to character classes, the second part encodes a deterministic finite automaton using these character classes as transitions.
1.8.17