nostr/damus
1
0
Fork 0
mirror of git://jb55.com/damus synced 2024-10-04 19:00:42 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix some incompatibility between nostrdb and damus'

Browse Source
This commit is contained in:
William Casarin 2023-12-02 13:41:36 -08:00
parent 8e361a9586
commit 65be56ba7c
1 changed files with 1 additions and 168 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

169
nostrdb/nostrdb.c
View File

@ -2124,173 +2124,6 @@ static int ndb_write_note_kind_index(struct ndb_txn *txn, struct ndb_note *note,
return 1; return 1;
} }
/**
* Checks if a given Unicode code point is a punctuation character
*
* @param codepoint The Unicode code point to check. @return true if the
* code point is a punctuation character, false otherwise.
*/
static inline int is_punctuation(unsigned int codepoint) {
// Check for underscore (underscore is not treated as punctuation)
if (codepoint == '_')
return 0;
// Check for ASCII punctuation
if (codepoint <= 128 && ispunct(codepoint))
return 1;
// Check for Unicode punctuation exceptions (punctuation allowed in hashtags)
if (codepoint == 0x301C || codepoint == 0xFF5E) // Japanese Wave Dash / Tilde
return 0;
// Check for Unicode punctuation
// NOTE: We may need to adjust the codepoint ranges in the future,
// to include/exclude certain types of Unicode characters in hashtags.
// Unicode Blocks Reference: https://www.compart.com/en/unicode/block
return (
// Latin-1 Supplement No-Break Space (NBSP): U+00A0
(codepoint == 0x00A0) ||
// Latin-1 Supplement Punctuation: U+00A1 to U+00BF
(codepoint >= 0x00A1 && codepoint <= 0x00BF) ||
// General Punctuation: U+2000 to U+206F
(codepoint >= 0x2000 && codepoint <= 0x206F) ||
// Currency Symbols: U+20A0 to U+20CF
(codepoint >= 0x20A0 && codepoint <= 0x20CF) ||
// Supplemental Punctuation: U+2E00 to U+2E7F
(codepoint >= 0x2E00 && codepoint <= 0x2E7F) ||
// CJK Symbols and Punctuation: U+3000 to U+303F
(codepoint >= 0x3000 && codepoint <= 0x303F) ||
// Ideographic Description Characters: U+2FF0 to U+2FFF
(codepoint >= 0x2FF0 && codepoint <= 0x2FFF)
);
}
static inline int is_whitespace(char c) {
return c == ' ' || c == '\t' || c == '\n' || c == '\v' || c == '\f' || c == '\r';
}
static inline int is_right_boundary(int c) {
return is_whitespace(c) || is_punctuation(c);
}
static inline int parse_byte(struct cursor *cursor, unsigned char *c)
{
if (unlikely(cursor->p >= cursor->end))
return 0;
*c = *cursor->p;
return 1;
}
static inline int peek_char(struct cursor *cur, int ind) {
if ((cur->p + ind < cur->start) || (cur->p + ind >= cur->end))
return -1;
return *(cur->p + ind);
}
static int parse_utf8_char(struct cursor *cursor, unsigned int *code_point,
unsigned int *utf8_length)
{
unsigned char first_byte;
if (!parse_byte(cursor, &first_byte))
return 0; // Not enough data
// Determine the number of bytes in this UTF-8 character
int remaining_bytes = 0;
if (first_byte < 0x80) {
*code_point = first_byte;
return 1;
} else if ((first_byte & 0xE0) == 0xC0) {
remaining_bytes = 1;
*utf8_length = remaining_bytes + 1;
*code_point = first_byte & 0x1F;
} else if ((first_byte & 0xF0) == 0xE0) {
remaining_bytes = 2;
*utf8_length = remaining_bytes + 1;
*code_point = first_byte & 0x0F;
} else if ((first_byte & 0xF8) == 0xF0) {
remaining_bytes = 3;
*utf8_length = remaining_bytes + 1;
*code_point = first_byte & 0x07;
} else {
remaining_bytes = 0;
*utf8_length = 1; // Assume 1 byte length for unrecognized UTF-8 characters
// TODO: We need to gracefully handle unrecognized UTF-8 characters
//printf("Invalid UTF-8 byte: %x\n", *code_point);
*code_point = ((first_byte & 0xF0) << 6); // Prevent testing as punctuation
return 0; // Invalid first byte
}
// Peek at remaining bytes
for (int i = 0; i < remaining_bytes; ++i) {
signed char next_byte;
if ((next_byte = peek_char(cursor, i+1)) == -1) {
*utf8_length = 1;
return 0; // Not enough data
}
if ((next_byte & 0xC0) != 0x80) {
*utf8_length = 1;
return 0; // Invalid byte in sequence
}
*code_point = (*code_point << 6) | (next_byte & 0x3F);
}
return 1;
}
static inline int is_utf8_byte(unsigned char c) {
return c & 0x80;
}
static inline int consume_until_boundary(struct cursor *cur) {
unsigned int c;
unsigned int char_length = 1;
unsigned int *utf8_char_length = &char_length;
while (cur->p < cur->end) {
c = *cur->p;
*utf8_char_length = 1;
if (is_whitespace(c))
return 1;
// Need to check for UTF-8 characters, which can be multiple
// bytes long
if (is_utf8_byte(c)) {
if (!parse_utf8_char(cur, &c, utf8_char_length)) {
if (!is_right_boundary(c)){
// TODO: We should work towards
// handling all UTF-8 characters.
//printf("Invalid UTF-8 code point: %x\n", c);
return 0;
}
}
}
if (is_right_boundary(c))
return 1;
// Need to use a variable character byte length for UTF-8 (2-4 bytes)
if (cur->p + *utf8_char_length <= cur->end)
cur->p += *utf8_char_length;
else
cur->p++;
}
return 1;
}
static void consume_whitespace_or_punctuation(struct cursor *cur) static void consume_whitespace_or_punctuation(struct cursor *cur)
{ {
while (cur->p < cur->end) { while (cur->p < cur->end) {
@ -3670,7 +3503,7 @@ static int ndb_event_commitment(struct ndb_note *ev, unsigned char *buf, int buf
struct cursor cur; struct cursor cur;
int ok; int ok;
if (!hex_encode(ev->pubkey, sizeof(ev->pubkey), pubkey)) if (!hex_encode(ev->pubkey, sizeof(ev->pubkey), pubkey, sizeof(pubkey)))
return 0; return 0;
make_cursor(buf, buf + buflen, &cur); make_cursor(buf, buf + buflen, &cur);