diff options
| -rw-r--r-- | src/xine-utils/xmllexer.c | 82 |
1 files changed, 50 insertions, 32 deletions
diff --git a/src/xine-utils/xmllexer.c b/src/xine-utils/xmllexer.c index 754a006f9..4198b197b 100644 --- a/src/xine-utils/xmllexer.c +++ b/src/xine-utils/xmllexer.c @@ -61,9 +61,27 @@ void lexer_init(const char * buf, int size) { lprintf("buffer length %d\n", size); } +typedef enum { + STATE_UNKNOWN = -1, + STATE_IDLE, + STATE_EOL, + STATE_SEPAR, + STATE_T_M_START, + STATE_T_M_STOP_1, + STATE_T_M_STOP_2, + STATE_T_EQUAL, + STATE_T_STRING_SINGLE, + STATE_T_STRING_DOUBLE, + STATE_T_COMMENT, + STATE_T_TI_STOP, + STATE_T_DASHDASH, + STATE_T_C_STOP, + STATE_IDENT /* must be last */ +} lexer_state_t; + int lexer_get_token(char * tok, int tok_size) { int tok_pos = 0; - int state = 0; + lexer_state_t state = STATE_IDLE; char c; if (tok) { @@ -75,69 +93,69 @@ int lexer_get_token(char * tok, int tok_size) { /* normal mode */ switch (state) { /* init state */ - case 0: + case STATE_IDLE: switch (c) { case '\n': case '\r': - state = 1; + state = STATE_EOL; tok[tok_pos] = c; tok_pos++; break; case ' ': case '\t': - state = 2; + state = STATE_SEPAR; tok[tok_pos] = c; tok_pos++; break; case '<': - state = 3; + state = STATE_T_M_START; tok[tok_pos] = c; tok_pos++; break; case '>': - state = 4; + state = STATE_T_M_STOP_1; tok[tok_pos] = c; tok_pos++; break; case '/': if (!in_comment) - state = 5; + state = STATE_T_M_STOP_2; tok[tok_pos] = c; tok_pos++; break; case '=': - state = 6; + state = STATE_T_EQUAL; tok[tok_pos] = c; tok_pos++; break; case '\"': /* " */ - state = 7; + state = STATE_T_STRING_DOUBLE; break; case '\'': /* " */ - state = 12; + state = STATE_T_STRING_SINGLE; break; case '-': - state = 10; + state = STATE_T_DASHDASH; tok[tok_pos] = c; tok_pos++; break; case '?': - state = 9; + state = STATE_T_TI_STOP; tok[tok_pos] = c; tok_pos++; break; default: - state = 100; + state = STATE_IDENT; tok[tok_pos] = c; tok_pos++; break; @@ -146,7 +164,7 @@ int lexer_get_token(char * tok, int tok_size) { break; /* end of line */ - case 1: + case STATE_EOL: if (c == '\n' || (c == '\r')) { tok[tok_pos] = c; lexbuf_pos++; @@ -158,7 +176,7 @@ int lexer_get_token(char * tok, int tok_size) { break; /* T_SEPAR */ - case 2: + case STATE_SEPAR: if (c == ' ' || (c == '\t')) { tok[tok_pos] = c; lexbuf_pos++; @@ -170,7 +188,7 @@ int lexer_get_token(char * tok, int tok_size) { break; /* T_M_START < or </ or <! or <? */ - case 3: + case STATE_T_M_START: switch (c) { case '/': tok[tok_pos] = c; @@ -183,7 +201,7 @@ int lexer_get_token(char * tok, int tok_size) { tok[tok_pos] = c; lexbuf_pos++; tok_pos++; - state = 8; + state = STATE_T_COMMENT; break; case '?': tok[tok_pos] = c; @@ -199,7 +217,7 @@ int lexer_get_token(char * tok, int tok_size) { break; /* T_M_STOP_1 */ - case 4: + case STATE_T_M_STOP_1: tok[tok_pos] = '\0'; if (!in_comment) lex_mode = DATA; @@ -207,7 +225,7 @@ int lexer_get_token(char * tok, int tok_size) { break; /* T_M_STOP_2 */ - case 5: + case STATE_T_M_STOP_2: if (c == '>') { tok[tok_pos] = c; lexbuf_pos++; @@ -223,13 +241,13 @@ int lexer_get_token(char * tok, int tok_size) { break; /* T_EQUAL */ - case 6: + case STATE_T_EQUAL: tok[tok_pos] = '\0'; return T_EQUAL; break; /* T_STRING */ - case 7: + case STATE_T_STRING_DOUBLE: tok[tok_pos] = c; lexbuf_pos++; if (c == '\"') { /* " */ @@ -240,7 +258,7 @@ int lexer_get_token(char * tok, int tok_size) { break; /* T_C_START or T_DOCTYPE_START */ - case 8: + case STATE_T_COMMENT: switch (c) { case '-': lexbuf_pos++; @@ -271,7 +289,7 @@ int lexer_get_token(char * tok, int tok_size) { break; /* T_TI_STOP */ - case 9: + case STATE_T_TI_STOP: if (c == '>') { tok[tok_pos] = c; lexbuf_pos++; @@ -285,24 +303,24 @@ int lexer_get_token(char * tok, int tok_size) { break; /* -- */ - case 10: + case STATE_T_DASHDASH: switch (c) { case '-': tok[tok_pos] = c; tok_pos++; lexbuf_pos++; - state = 11; + state = STATE_T_C_STOP; break; default: tok[tok_pos] = c; tok_pos++; lexbuf_pos++; - state = 100; + state = STATE_IDENT; } break; /* --> */ - case 11: + case STATE_T_C_STOP: switch (c) { case '>': tok[tok_pos] = c; @@ -322,12 +340,12 @@ int lexer_get_token(char * tok, int tok_size) { tok[tok_pos] = c; tok_pos++; lexbuf_pos++; - state = 100; + state = STATE_IDENT; } break; /* T_STRING (single quotes) */ - case 12: + case STATE_T_STRING_SINGLE: tok[tok_pos] = c; lexbuf_pos++; if (c == '\'') { /* " */ @@ -338,7 +356,7 @@ int lexer_get_token(char * tok, int tok_size) { break; /* IDENT */ - case 100: + case STATE_IDENT: switch (c) { case '<': case '>': @@ -355,13 +373,13 @@ int lexer_get_token(char * tok, int tok_size) { tok[tok_pos] = c; tok_pos++; lexbuf_pos++; - state = 9; + state = STATE_T_TI_STOP; break; case '-': tok[tok_pos] = c; tok_pos++; lexbuf_pos++; - state = 10; + state = STATE_T_DASHDASH; break; default: tok[tok_pos] = c; |