diff options
author | John Mark Bell <jmb@netsurf-browser.org> | 2008-07-31 14:43:32 +0000 |
---|---|---|
committer | John Mark Bell <jmb@netsurf-browser.org> | 2008-07-31 14:43:32 +0000 |
commit | 6d3950b141b1cdb1f29e929c8c8156562c7ccbc7 (patch) | |
tree | d2bb92960c4c3b54f083f1307241d5fdbac7fdfd /src/utils | |
parent | 2f7a0e956c151c900789a02d8f850bfe79b54071 (diff) | |
download | libhubbub-6d3950b141b1cdb1f29e929c8c8156562c7ccbc7.tar.gz libhubbub-6d3950b141b1cdb1f29e929c8c8156562c7ccbc7.tar.bz2 |
Merged revisions 4631-4838 via svnmerge from
svn://source.netsurf-browser.org/branches/takkaria/hubbub-parserutils
........
r4631 | takkaria | 2008-07-13 12:54:30 +0100 (Sun, 13 Jul 2008) | 2 lines
Initial hatchet job moving to libparserutils (search and replace and a bit of cleaning up). This doesn't compile.
........
r4632 | takkaria | 2008-07-13 15:28:52 +0100 (Sun, 13 Jul 2008) | 2 lines
libparserutilize everything up to the "before attribute name" state. (Not compiling)
........
r4633 | takkaria | 2008-07-13 15:32:14 +0100 (Sun, 13 Jul 2008) | 2 lines
Replace all uses of "current_{comment|chars}" with just "chars".
........
r4634 | takkaria | 2008-07-13 16:12:06 +0100 (Sun, 13 Jul 2008) | 2 lines
Fix lots of compile errors, lpuise "before attribute name" state.
........
r4636 | takkaria | 2008-07-13 17:23:17 +0100 (Sun, 13 Jul 2008) | 2 lines
Finish lpuising the tag states, apart from character references.
........
r4637 | takkaria | 2008-07-13 19:58:52 +0100 (Sun, 13 Jul 2008) | 2 lines
lpuise the comment states.
........
r4638 | takkaria | 2008-07-13 20:04:31 +0100 (Sun, 13 Jul 2008) | 2 lines
Switch to setting hubbub_string::len to 0 instead of hubbub_string::ptr to NULL to indicate an empty buffer, as it was previously.
........
r4639 | takkaria | 2008-07-13 21:02:11 +0100 (Sun, 13 Jul 2008) | 2 lines
"lpu up" about half of the DOCTYPE handling stages.
........
r4640 | takkaria | 2008-07-13 21:23:00 +0100 (Sun, 13 Jul 2008) | 2 lines
Finish off LPUing the doctype modes.
........
r4641 | takkaria | 2008-07-13 21:37:33 +0100 (Sun, 13 Jul 2008) | 2 lines
The tokeniser uses lpu apart from the entity matcher, now.
........
r4643 | takkaria | 2008-07-14 01:20:36 +0100 (Mon, 14 Jul 2008) | 2 lines
Fix up the character reference matching stuff--still not properly dealt with, but compiles futher.
........
r4644 | takkaria | 2008-07-14 01:24:49 +0100 (Mon, 14 Jul 2008) | 2 lines
Get the tokeniser compiling in its LPU'd form.
........
r4645 | takkaria | 2008-07-14 01:26:34 +0100 (Mon, 14 Jul 2008) | 2 lines
Remember to advance the stream position after emitting tokens.
........
r4646 | takkaria | 2008-07-14 01:34:36 +0100 (Mon, 14 Jul 2008) | 2 lines
Nuke the src/input directory and start work on the treebuilder.
........
r4647 | takkaria | 2008-07-14 01:56:27 +0100 (Mon, 14 Jul 2008) | 2 lines
Get hubbub building in its LPU'd form.
........
r4648 | takkaria | 2008-07-14 02:41:03 +0100 (Mon, 14 Jul 2008) | 2 lines
Get the tokeniser2 testrunner working.
........
r4649 | takkaria | 2008-07-14 02:48:55 +0100 (Mon, 14 Jul 2008) | 2 lines
Fix test LDFLAGS so things link properly.
........
r4650 | takkaria | 2008-07-14 16:25:51 +0100 (Mon, 14 Jul 2008) | 2 lines
Get testcases compiling, remove ones now covered by libparserutils.
........
r4651 | takkaria | 2008-07-14 16:37:09 +0100 (Mon, 14 Jul 2008) | 2 lines
Remove more tests covered by libpu.
........
r4652 | takkaria | 2008-07-14 17:53:18 +0100 (Mon, 14 Jul 2008) | 2 lines
Fix up the tokeniser a bit.
........
r4653 | takkaria | 2008-07-14 19:02:15 +0100 (Mon, 14 Jul 2008) | 3 lines
- Remove the buffer_handler stuff from hubbub
- Add the basics of a buffer for attribute values and text.
........
r4654 | takkaria | 2008-07-14 20:00:45 +0100 (Mon, 14 Jul 2008) | 2 lines
Get character references working in attribute values, start trying to make them work in character tokens.
........
r4656 | takkaria | 2008-07-14 23:28:52 +0100 (Mon, 14 Jul 2008) | 2 lines
Get entities working a bit better.
........
r4657 | takkaria | 2008-07-14 23:37:16 +0100 (Mon, 14 Jul 2008) | 2 lines
Get entities working properly. (!)
........
r4658 | takkaria | 2008-07-14 23:56:10 +0100 (Mon, 14 Jul 2008) | 2 lines
Make doctypes work a bit better.
........
r4659 | takkaria | 2008-07-15 00:18:49 +0100 (Tue, 15 Jul 2008) | 2 lines
Get DOCTYPEs working.
........
r4660 | takkaria | 2008-07-15 00:26:36 +0100 (Tue, 15 Jul 2008) | 2 lines
Fix CDATA sections.
........
r4661 | takkaria | 2008-07-15 01:01:16 +0100 (Tue, 15 Jul 2008) | 2 lines
Get comments working again.
........
r4662 | takkaria | 2008-07-15 01:14:19 +0100 (Tue, 15 Jul 2008) | 2 lines
Fix EOF in "after attribute name" state.
........
r4664 | takkaria | 2008-07-15 01:30:27 +0100 (Tue, 15 Jul 2008) | 2 lines
Put the tests in better order, remove one now superceded with libpu.
........
r4665 | takkaria | 2008-07-15 01:46:29 +0100 (Tue, 15 Jul 2008) | 2 lines
Remove a lot of now-redunant clearings of the current stream offset.
........
r4667 | jmb | 2008-07-15 11:56:54 +0100 (Tue, 15 Jul 2008) | 2 lines
Completely purge charset stuff from hubbub. Parserutils handles this now.
........
r4677 | takkaria | 2008-07-15 21:03:42 +0100 (Tue, 15 Jul 2008) | 2 lines
Get more tests passing, handle NUL bytes in data state.
........
r4694 | takkaria | 2008-07-18 17:55:44 +0100 (Fri, 18 Jul 2008) | 3 lines
- Handle CRs correctly in some token states.
- Handle NULs correctly in the CDATA state.
........
r4706 | takkaria | 2008-07-19 14:58:48 +0100 (Sat, 19 Jul 2008) | 2 lines
Improve the tokeniser2 output a bit.
........
r4721 | takkaria | 2008-07-21 20:57:29 +0100 (Mon, 21 Jul 2008) | 2 lines
Get a better framework in place to allow switching to using a buffer mid-collect. This fails a couple of testcases and doesn't implement proper CR or NUL support yet.
........
r4725 | takkaria | 2008-07-23 17:20:07 +0100 (Wed, 23 Jul 2008) | 2 lines
Make comment tokens in tokeniser2 display both expected and actual output.
........
r4726 | takkaria | 2008-07-23 19:10:23 +0100 (Wed, 23 Jul 2008) | 4 lines
- Add FINISH() macro which stops using buffered character collection.
- Make the encoding U+FFFD in UTF-8 a global varabile, for sanity
- Make the bogus comment state deal with NULs correctly.
........
r4730 | takkaria | 2008-07-24 00:35:16 +0100 (Thu, 24 Jul 2008) | 2 lines
Try to get NUL bytes handled as the spec says.
........
r4731 | takkaria | 2008-07-24 00:40:59 +0100 (Thu, 24 Jul 2008) | 2 lines
Get CRs working in the data state.
........
r4732 | takkaria | 2008-07-24 00:47:45 +0100 (Thu, 24 Jul 2008) | 2 lines
Set force-quirks correctly when failing to match PUBLIC or SYSTEM in DOCTYPEs.
........
r4773 | takkaria | 2008-07-28 15:34:41 +0100 (Mon, 28 Jul 2008) | 2 lines
Fix up the tokeniser, finally.
........
r4801 | takkaria | 2008-07-29 15:59:31 +0100 (Tue, 29 Jul 2008) | 2 lines
Refactor macros a bit.
........
r4802 | takkaria | 2008-07-29 16:04:17 +0100 (Tue, 29 Jul 2008) | 2 lines
Do s/HUBBUB_TOKENISER_STATE_/STATE_/, for shorter line lengths.
........
r4805 | takkaria | 2008-07-29 16:58:37 +0100 (Tue, 29 Jul 2008) | 4 lines
Start cleaning up the hubbub tokeniser;
- refactor to use new inline emit_character_token() and emit_current_tag() functions; makes code clearer
- check EOF before using the CHAR() macro, so eventually it can be removed.
........
r4806 | takkaria | 2008-07-29 17:45:36 +0100 (Tue, 29 Jul 2008) | 2 lines
More cleanup like the previous commit.
........
r4807 | takkaria | 2008-07-29 19:48:44 +0100 (Tue, 29 Jul 2008) | 2 lines
Rewrite comment-handling code to be just the one function, whilst updating it to handle CRs and NULs properly. (All comments now always use the buffer.)
........
r4820 | takkaria | 2008-07-30 14:14:49 +0100 (Wed, 30 Jul 2008) | 2 lines
Finish off the first sweep of cleaning up and refactoring the tokeniser.
........
r4821 | takkaria | 2008-07-30 15:12:22 +0100 (Wed, 30 Jul 2008) | 2 lines
Add copyright statement.
........
r4822 | takkaria | 2008-07-30 17:23:01 +0100 (Wed, 30 Jul 2008) | 2 lines
Apply changes made to tokeniser2 to tokeniser3.
........
r4829 | takkaria | 2008-07-31 01:59:07 +0100 (Thu, 31 Jul 2008) | 4 lines
- Make the tokeniser save everything into the buffer, at least for now.
- Fix logic errors introduced in refactoring
- Avoid emitting more tokens than we have to (e.g. instead of emitting "<>" and switching back to the data state, just switch back to the data state and let it take care of it)
........
r4830 | takkaria | 2008-07-31 02:03:08 +0100 (Thu, 31 Jul 2008) | 2 lines
Small treebuilder <isindex> fix.
........
r4831 | takkaria | 2008-07-31 02:32:29 +0100 (Thu, 31 Jul 2008) | 2 lines
Stop holding on to pointers to character data across treebuilder calls.
........
r4832 | takkaria | 2008-07-31 02:45:09 +0100 (Thu, 31 Jul 2008) | 18 lines
Merge revisions 4620-4831 from trunk hubbub to libinputstream hubbub, modulo one change to test/Makefile which makes the linker choke when linking tests.
------------------------------------------------------------------------
r4666 | jmb | 2008-07-15 11:52:13 +0100 (Tue, 15 Jul 2008) | 3 lines
Make tree2 perform reference counting.
Fix bits of the treebuilder to perform reference counting correctly in the face of *result not pointing to the same object as the node passed in to the treebuilder client callbacks.
------------------------------------------------------------------------
r4668 | jmb | 2008-07-15 12:37:30 +0100 (Tue, 15 Jul 2008) | 2 lines
Fully document treebuilder callbacks.
------------------------------------------------------------------------
r4675 | takkaria | 2008-07-15 21:01:03 +0100 (Tue, 15 Jul 2008) | 2 lines
Fix memory leak in tokeniser2.
------------------------------------------------------------------------
........
r4834 | jmb | 2008-07-31 09:57:51 +0100 (Thu, 31 Jul 2008) | 2 lines
Fix infinite loop in charset detector
........
r4835 | jmb | 2008-07-31 13:01:24 +0100 (Thu, 31 Jul 2008) | 2 lines
Actually store namespaces on formatting list. Otherwise we read uninitialised memory. Add some semblance of filling allocations with junk to myrealloc().
........
r4836 | jmb | 2008-07-31 13:06:07 +0100 (Thu, 31 Jul 2008) | 2 lines
Lose debug again
........
r4837 | jmb | 2008-07-31 15:09:19 +0100 (Thu, 31 Jul 2008) | 2 lines
Lose obsolete testdata (this is now part of lpu)
........
svn path=/trunk/hubbub/; revision=4839
Diffstat (limited to 'src/utils')
-rw-r--r-- | src/utils/Makefile | 2 | ||||
-rw-r--r-- | src/utils/utf16.c | 239 | ||||
-rw-r--r-- | src/utils/utf16.h | 38 | ||||
-rw-r--r-- | src/utils/utf8.c | 368 | ||||
-rw-r--r-- | src/utils/utf8.h | 38 |
5 files changed, 1 insertions, 684 deletions
diff --git a/src/utils/Makefile b/src/utils/Makefile index 1910dc0..0678442 100644 --- a/src/utils/Makefile +++ b/src/utils/Makefile @@ -32,7 +32,7 @@ dirstack_$(sp) := $(d) d := $(DIR) # Sources -SRCS_$(d) := dict.c errors.c utf8.c utf16.c string.c +SRCS_$(d) := dict.c errors.c string.c # Append to sources for component SOURCES += $(addprefix $(d), $(SRCS_$(d))) diff --git a/src/utils/utf16.c b/src/utils/utf16.c deleted file mode 100644 index a295109..0000000 --- a/src/utils/utf16.c +++ /dev/null @@ -1,239 +0,0 @@ -/* - * This file is part of Hubbub. - * Licensed under the MIT License, - * http://www.opensource.org/licenses/mit-license.php - * Copyright 2007 John-Mark Bell <jmb@netsurf-browser.org> - */ - -/** \file - * UTF-16 manipulation functions (implementation). - */ - -#include <stdbool.h> -#include <stdlib.h> -#include <string.h> - -#include "utils/utf16.h" - -/** - * Convert a UTF-16 sequence into a single UCS4 character - * - * \param s The sequence to process - * \param len Length of sequence - * \param ucs4 Pointer to location to receive UCS4 character (host endian) - * \param clen Pointer to location to receive byte length of UTF-16 sequence - * \return HUBBUB_OK on success, appropriate error otherwise - */ -hubbub_error hubbub_utf16_to_ucs4(const uint8_t *s, size_t len, - uint32_t *ucs4, size_t *clen) -{ - const uint16_t *ss = (const uint16_t *) (const void *) s; - - if (s == NULL || ucs4 == NULL || clen == NULL) - return HUBBUB_BADPARM; - - if (len < 2) - return HUBBUB_NEEDDATA; - - if (*ss < 0xD800 || *ss > 0xDFFF) { - *ucs4 = *ss; - *clen = 2; - } else if (0xD800 <= *ss && *ss <= 0xBFFF) { - if (len < 4) - return HUBBUB_NEEDDATA; - - if (0xDC00 <= ss[1] && ss[1] <= 0xE000) { - *ucs4 = (((s[0] >> 6) & 0x1f) + 1) | - ((s[0] & 0x3f) | (s[1] & 0x3ff)); - *clen = 4; - } else { - return HUBBUB_INVALID; - } - } - - return HUBBUB_OK; -} - -/** - * Convert a single UCS4 character into a UTF-16 sequence - * - * \param ucs4 The character to process (0 <= c <= 0x7FFFFFFF) (host endian) - * \param s Pointer to 4 byte long output buffer - * \param len Pointer to location to receive length of multibyte sequence - * \return HUBBUB_OK on success, appropriate error otherwise - */ -hubbub_error hubbub_utf16_from_ucs4(uint32_t ucs4, uint8_t *s, - size_t *len) -{ - uint16_t *ss = (uint16_t *) (void *) s; - uint32_t l = 0; - - if (s == NULL || len == NULL) - return HUBBUB_BADPARM; - else if (ucs4 < 0x10000) { - *ss = (uint16_t) ucs4; - l = 2; - } else if (ucs4 < 0x110000) { - ss[0] = 0xD800 | (((ucs4 >> 16) & 0x1f) - 1) | (ucs4 >> 10); - ss[1] = 0xDC00 | (ucs4 & 0x3ff); - l = 4; - } else { - return HUBBUB_INVALID; - } - - *len = l; - - return HUBBUB_OK; -} - -/** - * Calculate the length (in characters) of a bounded UTF-16 string - * - * \param s The string - * \param max Maximum length - * \param len Pointer to location to receive length of string - * \return HUBBUB_OK on success, appropriate error otherwise - */ -hubbub_error hubbub_utf16_length(const uint8_t *s, size_t max, - size_t *len) -{ - const uint16_t *ss = (const uint16_t *) (const void *) s; - const uint16_t *end = (const uint16_t *) (const void *) (s + max); - int l = 0; - - if (s == NULL || len == NULL) - return HUBBUB_BADPARM; - - while (ss < end) { - if (*ss < 0xD800 || 0xDFFF < *ss) - ss++; - else - ss += 2; - - l++; - } - - *len = l; - - return HUBBUB_OK; -} - -/** - * Calculate the length (in bytes) of a UTF-16 character - * - * \param s Pointer to start of character - * \param len Pointer to location to receive length - * \return HUBBUB_OK on success, appropriate error otherwise - */ -hubbub_error hubbub_utf16_char_byte_length(const uint8_t *s, - size_t *len) -{ - const uint16_t *ss = (const uint16_t *) (const void *) s; - - if (s == NULL || len == NULL) - return HUBBUB_BADPARM; - - if (*ss < 0xD800 || 0xDFFF < *ss) - *len = 2; - else - *len = 4; - - return HUBBUB_OK; -} - -/** - * Find previous legal UTF-16 char in string - * - * \param s The string - * \param off Offset in the string to start at - * \param prevoff Pointer to location to receive offset of first byte of - * previous legal character - * \return HUBBUB_OK on success, appropriate error otherwise - */ -hubbub_error hubbub_utf16_prev(const uint8_t *s, uint32_t off, - uint32_t *prevoff) -{ - const uint16_t *ss = (const uint16_t *) (const void *) s; - - if (s == NULL || prevoff == NULL) - return HUBBUB_BADPARM; - - if (off < 2) - *prevoff = 0; - else if (ss[-1] < 0xDC00 || ss[-1] > 0xDFFF) - *prevoff = off - 2; - else - *prevoff = (off < 4) ? 0 : off - 4; - - return HUBBUB_OK; -} - -/** - * Find next legal UTF-16 char in string - * - * \param s The string (assumed valid) - * \param len Maximum offset in string - * \param off Offset in the string to start at - * \param nextoff Pointer to location to receive offset of first byte of - * next legal character - * \return HUBBUB_OK on success, appropriate error otherwise - */ -hubbub_error hubbub_utf16_next(const uint8_t *s, uint32_t len, - uint32_t off, uint32_t *nextoff) -{ - const uint16_t *ss = (const uint16_t *) (const void *) s; - - if (s == NULL || off >= len || nextoff == NULL) - return HUBBUB_BADPARM; - - if (len - off < 4) - *nextoff = len; - else if (ss[1] < 0xD800 || ss[1] > 0xDBFF) - *nextoff = off + 2; - else - *nextoff = (len - off < 6) ? len : off + 4; - - return HUBBUB_OK; -} - -/** - * Find next legal UTF-16 char in string - * - * \param s The string (assumed to be of dubious validity) - * \param len Maximum offset in string - * \param off Offset in the string to start at - * \param nextoff Pointer to location to receive offset of first byte of - * next legal character - * \return HUBBUB_OK on success, appropriate error otherwise - */ -hubbub_error hubbub_utf16_next_paranoid(const uint8_t *s, - uint32_t len, uint32_t off, uint32_t *nextoff) -{ - const uint16_t *ss = (const uint16_t *) (const void *) s; - - if (s == NULL || off >= len || nextoff == NULL) - return HUBBUB_BADPARM; - - while (1) { - if (len - off < 4) { - return HUBBUB_NEEDDATA; - } else if (ss[1] < 0xD800 || ss[1] > 0xDFFF) { - *nextoff = off + 2; - break; - } else if (ss[1] >= 0xD800 && ss[1] <= 0xDBFF) { - if (len - off < 6) - return HUBBUB_NEEDDATA; - - if (ss[2] >= 0xDC00 && ss[2] <= 0xDFFF) { - *nextoff = off + 4; - break; - } else { - ss++; - off += 2; - } - } - } - - return HUBBUB_OK; -} - diff --git a/src/utils/utf16.h b/src/utils/utf16.h deleted file mode 100644 index 2cea38d..0000000 --- a/src/utils/utf16.h +++ /dev/null @@ -1,38 +0,0 @@ -/* - * This file is part of Hubbub. - * Licensed under the MIT License, - * http://www.opensource.org/licenses/mit-license.php - * Copyright 2007 John-Mark Bell <jmb@netsurf-browser.org> - */ - -/** \file - * UTF-16 manipulation functions (interface). - */ - -#ifndef hubbub_utils_utf16_h_ -#define hubbub_utils_utf16_h_ - -#include <inttypes.h> - -#include <hubbub/errors.h> - -hubbub_error hubbub_utf16_to_ucs4(const uint8_t *s, size_t len, - uint32_t *ucs4, size_t *clen); -hubbub_error hubbub_utf16_from_ucs4(uint32_t ucs4, uint8_t *s, - size_t *len); - -hubbub_error hubbub_utf16_length(const uint8_t *s, size_t max, - size_t *len); -hubbub_error hubbub_utf16_char_byte_length(const uint8_t *s, - size_t *len); - -hubbub_error hubbub_utf16_prev(const uint8_t *s, uint32_t off, - uint32_t *prevoff); -hubbub_error hubbub_utf16_next(const uint8_t *s, uint32_t len, - uint32_t off, uint32_t *nextoff); - -hubbub_error hubbub_utf16_next_paranoid(const uint8_t *s, - uint32_t len, uint32_t off, uint32_t *nextoff); - -#endif - diff --git a/src/utils/utf8.c b/src/utils/utf8.c deleted file mode 100644 index 08a1853..0000000 --- a/src/utils/utf8.c +++ /dev/null @@ -1,368 +0,0 @@ -/* - * This file is part of Hubbub. - * Licensed under the MIT License, - * http://www.opensource.org/licenses/mit-license.php - * Copyright 2007 John-Mark Bell <jmb@netsurf-browser.org> - */ - -/** \file - * UTF-8 manipulation functions (implementation). - */ - -#include <stdbool.h> -#include <stdlib.h> -#include <string.h> - -#include "utils/utf8.h" - -/** Number of continuation bytes for a given start byte */ -static const uint8_t numContinuations[256] = { - 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, - 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, - 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, - 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, - 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, - 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, - 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, - 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, - 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, - 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, - 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, - 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, - 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, - 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, - 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, - 3, 3, 3, 3, 3, 3, 3, 3, 4, 4, 4, 4, 5, 5, 5, 5, -}; - -/** - * Convert a UTF-8 multibyte sequence into a single UCS4 character - * - * Encoding of UCS values outside the UTF-16 plane has been removed from - * RFC3629. This function conforms to RFC2279, however. - * - * \param s The sequence to process - * \param len Length of sequence - * \param ucs4 Pointer to location to receive UCS4 character (host endian) - * \param clen Pointer to location to receive byte length of UTF-8 sequence - * \return HUBBUB_OK on success, appropriate error otherwise - */ -hubbub_error hubbub_utf8_to_ucs4(const uint8_t *s, size_t len, - uint32_t *ucs4, size_t *clen) -{ - if (s == NULL || ucs4 == NULL || clen == NULL) - return HUBBUB_BADPARM; - - if (len == 0) - return HUBBUB_NEEDDATA; - - if (*s < 0x80) { - *ucs4 = *s; - *clen = 1; - } else if ((*s & 0xE0) == 0xC0) { - if (len < 2) - return HUBBUB_NEEDDATA; - else if ((*(s+1) & 0xC0) != 0x80) - return HUBBUB_INVALID; - else { - *ucs4 = ((*s & 0x1F) << 6) | (*(s+1) & 0x3F); - *clen = 2; - } - } else if ((*s & 0xF0) == 0xE0) { - if (len < 3) - return HUBBUB_NEEDDATA; - else if ((*(s+1) & 0xC0) != 0x80 || - (*(s+2) & 0xC0) != 0x80) - return HUBBUB_INVALID; - else { - *ucs4 = ((*s & 0x0F) << 12) | - ((*(s+1) & 0x3F) << 6) | - (*(s+2) & 0x3F); - *clen = 3; - } - } else if ((*s & 0xF8) == 0xF0) { - if (len < 4) - return HUBBUB_NEEDDATA; - else if ((*(s+1) & 0xC0) != 0x80 || - (*(s+2) & 0xC0) != 0x80 || - (*(s+3) & 0xC0) != 0x80) - return HUBBUB_INVALID; - else { - *ucs4 = ((*s & 0x0F) << 18) | - ((*(s+1) & 0x3F) << 12) | - ((*(s+2) & 0x3F) << 6) | - (*(s+3) & 0x3F); - *clen = 4; - } - } else if ((*s & 0xFC) == 0xF8) { - if (len < 5) - return HUBBUB_NEEDDATA; - else if ((*(s+1) & 0xC0) != 0x80 || - (*(s+2) & 0xC0) != 0x80 || - (*(s+3) & 0xC0) != 0x80 || - (*(s+4) & 0xC0) != 0x80) - return HUBBUB_INVALID; - else { - *ucs4 = ((*s & 0x0F) << 24) | - ((*(s+1) & 0x3F) << 18) | - ((*(s+2) & 0x3F) << 12) | - ((*(s+3) & 0x3F) << 6) | - (*(s+4) & 0x3F); - *clen = 5; - } - } else if ((*s & 0xFE) == 0xFC) { - if (len < 6) - return HUBBUB_NEEDDATA; - else if ((*(s+1) & 0xC0) != 0x80 || - (*(s+2) & 0xC0) != 0x80 || - (*(s+3) & 0xC0) != 0x80 || - (*(s+4) & 0xC0) != 0x80 || - (*(s+5) & 0xC0) != 0x80) - return HUBBUB_INVALID; - else { - *ucs4 = ((*s & 0x0F) << 28) | - ((*(s+1) & 0x3F) << 24) | - ((*(s+2) & 0x3F) << 18) | - ((*(s+3) & 0x3F) << 12) | - ((*(s+4) & 0x3F) << 6) | - (*(s+5) & 0x3F); - *clen = 6; - } - } else { - return HUBBUB_INVALID; - } - - return HUBBUB_OK; -} - -/** - * Convert a single UCS4 character into a UTF-8 multibyte sequence - * - * Encoding of UCS values outside the UTF-16 plane has been removed from - * RFC3629. This function conforms to RFC2279, however. - * - * \param ucs4 The character to process (0 <= c <= 0x7FFFFFFF) (host endian) - * \param s Pointer to 6 byte long output buffer - * \param len Pointer to location to receive length of multibyte sequence - * \return HUBBUB_OK on success, appropriate error otherwise - */ -hubbub_error hubbub_utf8_from_ucs4(uint32_t ucs4, uint8_t *s, - size_t *len) -{ - uint32_t l = 0; - - if (s == NULL || len == NULL) - return HUBBUB_BADPARM; - else if (ucs4 < 0x80) { - *s = (uint8_t) ucs4; - l = 1; - } else if (ucs4 < 0x800) { - *s = 0xC0 | ((ucs4 >> 6) & 0x1F); - *(s+1) = 0x80 | (ucs4 & 0x3F); - l = 2; - } else if (ucs4 < 0x10000) { - *s = 0xE0 | ((ucs4 >> 12) & 0xF); - *(s+1) = 0x80 | ((ucs4 >> 6) & 0x3F); - *(s+2) = 0x80 | (ucs4 & 0x3F); - l = 3; - } else if (ucs4 < 0x200000) { - *s = 0xF0 | ((ucs4 >> 18) & 0x7); - *(s+1) = 0x80 | ((ucs4 >> 12) & 0x3F); - *(s+2) = 0x80 | ((ucs4 >> 6) & 0x3F); - *(s+3) = 0x80 | (ucs4 & 0x3F); - l = 4; - } else if (ucs4 < 0x4000000) { - *s = 0xF8 | ((ucs4 >> 24) & 0x3); - *(s+1) = 0x80 | ((ucs4 >> 18) & 0x3F); - *(s+2) = 0x80 | ((ucs4 >> 12) & 0x3F); - *(s+3) = 0x80 | ((ucs4 >> 6) & 0x3F); - *(s+4) = 0x80 | (ucs4 & 0x3F); - l = 5; - } else if (ucs4 <= 0x7FFFFFFF) { - *s = 0xFC | ((ucs4 >> 30) & 0x1); - *(s+1) = 0x80 | ((ucs4 >> 24) & 0x3F); - *(s+2) = 0x80 | ((ucs4 >> 18) & 0x3F); - *(s+3) = 0x80 | ((ucs4 >> 12) & 0x3F); - *(s+4) = 0x80 | ((ucs4 >> 6) & 0x3F); - *(s+5) = 0x80 | (ucs4 & 0x3F); - l = 6; - } else { - return HUBBUB_INVALID; - } - - *len = l; - - return HUBBUB_OK; -} - -/** - * Calculate the length (in characters) of a bounded UTF-8 string - * - * \param s The string - * \param max Maximum length - * \param len Pointer to location to receive length of string - * \return HUBBUB_OK on success, appropriate error otherwise - */ -hubbub_error hubbub_utf8_length(const uint8_t *s, size_t max, - size_t *len) -{ - const uint8_t *end = s + max; - int l = 0; - - if (s == NULL || len == NULL) - return HUBBUB_BADPARM; - - while (s < end) { - if ((*s & 0x80) == 0x00) - s += 1; - else if ((*s & 0xE0) == 0xC0) - s += 2; - else if ((*s & 0xF0) == 0xE0) - s += 3; - else if ((*s & 0xF8) == 0xF0) - s += 4; - else if ((*s & 0xFC) == 0xF8) - s += 5; - else if ((*s & 0xFE) == 0xFC) - s += 6; - else - return HUBBUB_INVALID; - l++; - } - - *len = l; - - return HUBBUB_OK; -} - -/** - * Calculate the length (in bytes) of a UTF-8 character - * - * \param s Pointer to start of character - * \param len Pointer to location to receive length - * \return HUBBUB_OK on success, appropriate error otherwise - */ -hubbub_error hubbub_utf8_char_byte_length(const uint8_t *s, - size_t *len) -{ - if (s == NULL || len == NULL) - return HUBBUB_BADPARM; - - *len = numContinuations[s[0]] + 1 /* Start byte */; - - return HUBBUB_OK; -} - -/** - * Find previous legal UTF-8 char in string - * - * \param s The string - * \param off Offset in the string to start at - * \param prevoff Pointer to location to receive offset of first byte of - * previous legal character - * \return HUBBUB_OK on success, appropriate error otherwise - */ -hubbub_error hubbub_utf8_prev(const uint8_t *s, uint32_t off, - uint32_t *prevoff) -{ - if (s == NULL || prevoff == NULL) - return HUBBUB_BADPARM; - - while (off != 0 && (s[--off] & 0xC0) == 0x80) - /* do nothing */; - - *prevoff = off; - - return HUBBUB_OK; -} - -/** - * Find next legal UTF-8 char in string - * - * \param s The string (assumed valid) - * \param len Maximum offset in string - * \param off Offset in the string to start at - * \param nextoff Pointer to location to receive offset of first byte of - * next legal character - * \return HUBBUB_OK on success, appropriate error otherwise - */ -hubbub_error hubbub_utf8_next(const uint8_t *s, uint32_t len, - uint32_t off, uint32_t *nextoff) -{ - if (s == NULL || off >= len || nextoff == NULL) - return HUBBUB_BADPARM; - - /* Skip current start byte (if present - may be mid-sequence) */ - if (s[off] < 0x80 || (s[off] & 0xC0) == 0xC0) - off++; - - while (off < len && (s[off] & 0xC0) == 0x80) - off++; - - *nextoff = off; - - return HUBBUB_OK; -} - -/** - * Find next legal UTF-8 char in string - * - * \param s The string (assumed to be of dubious validity) - * \param len Maximum offset in string - * \param off Offset in the string to start at - * \param nextoff Pointer to location to receive offset of first byte of - * next legal character - * \return HUBBUB_OK on success, appropriate error otherwise - */ -hubbub_error hubbub_utf8_next_paranoid(const uint8_t *s, uint32_t len, - uint32_t off, uint32_t *nextoff) -{ - bool valid; - - if (s == NULL || off >= len || nextoff == NULL) - return HUBBUB_BADPARM; - - /* Skip current start byte (if present - may be mid-sequence) */ - if (s[off] < 0x80 || (s[off] & 0xC0) == 0xC0) - off++; - - while (1) { - /* Find next possible start byte */ - while (off < len && (s[off] & 0xC0) == 0x80) - off++; - - /* Ran off end of data */ - if (off == len || off + numContinuations[s[off]] >= len) - return HUBBUB_NEEDDATA; - - /* Found if start byte is ascii, - * or next n bytes are valid continuations */ - valid = true; - - switch (numContinuations[s[off]]) { - case 5: - valid &= ((s[off + 5] & 0xC0) == 0x80); - case 4: - valid &= ((s[off + 4] & 0xC0) == 0x80); - case 3: - valid &= ((s[off + 3] & 0xC0) == 0x80); - case 2: - valid &= ((s[off + 2] & 0xC0) == 0x80); - case 1: - valid &= ((s[off + 1] & 0xC0) == 0x80); - case 0: - valid &= (s[off + 0] < 0x80); - } - - if (valid) - break; - - /* Otherwise, skip this (invalid) start byte and try again */ - off++; - } - - *nextoff = off; - - return HUBBUB_OK; -} - diff --git a/src/utils/utf8.h b/src/utils/utf8.h deleted file mode 100644 index f2eedcb..0000000 --- a/src/utils/utf8.h +++ /dev/null @@ -1,38 +0,0 @@ -/* - * This file is part of Hubbub. - * Licensed under the MIT License, - * http://www.opensource.org/licenses/mit-license.php - * Copyright 2007 John-Mark Bell <jmb@netsurf-browser.org> - */ - -/** \file - * UTF-8 manipulation functions (interface). - */ - -#ifndef hubbub_utils_utf8_h_ -#define hubbub_utils_utf8_h_ - -#include <inttypes.h> - -#include <hubbub/errors.h> - -hubbub_error hubbub_utf8_to_ucs4(const uint8_t *s, size_t len, - uint32_t *ucs4, size_t *clen); -hubbub_error hubbub_utf8_from_ucs4(uint32_t ucs4, uint8_t *s, - size_t *len); - -hubbub_error hubbub_utf8_length(const uint8_t *s, size_t max, - size_t *len); -hubbub_error hubbub_utf8_char_byte_length(const uint8_t *s, - size_t *len); - -hubbub_error hubbub_utf8_prev(const uint8_t *s, uint32_t off, - uint32_t *prevoff); -hubbub_error hubbub_utf8_next(const uint8_t *s, uint32_t len, - uint32_t off, uint32_t *nextoff); - -hubbub_error hubbub_utf8_next_paranoid(const uint8_t *s, uint32_t len, - uint32_t off, uint32_t *nextoff); - -#endif - |