parser.l 5.4 KB
Newer Older
Teodor Sigaev's avatar
Teodor Sigaev committed
1 2 3 4 5 6 7 8 9 10 11
%{
#include "postgres.h"

#include "deflex.h"
#include "parser.h"
#include "common.h"

/* Avoid exit() on fatal scanner errors */
#define fprintf(file, fmt, msg)  ts_error(ERROR, fmt, msg)

char *token = NULL;  /* pointer to token */
12
int tokenlen;
Teodor Sigaev's avatar
Teodor Sigaev committed
13 14 15 16 17 18 19 20
char *s     = NULL;  /* to return WHOLE hyphenated-word */

YY_BUFFER_STATE buf = NULL; /* buffer to parse; it need for parse from string */

%}

%option 8bit
%option never-interactive
21
%option nodefault
Teodor Sigaev's avatar
Teodor Sigaev committed
22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284
%option nounput
%option noyywrap

/* parser's state for parsing hyphenated-word */
%x DELIM  
/* parser's state for parsing URL*/
%x URL  
%x SERVER  

/* parser's state for parsing TAGS */
%x INTAG
%x QINTAG
%x INCOMMENT
%x INSCRIPT

/* cyrillic koi8 char */
CYRALNUM	[0-9\200-\377]
CYRALPHA	[\200-\377]
ALPHA		[a-zA-Z\200-\377]
ALNUM		[0-9a-zA-Z\200-\377]


HOSTNAME	([-_[:alnum:]]+\.)+[[:alpha:]]+
URI		[-_[:alnum:]/%,\.;=&?#]+

%%

"<"[Ss][Cc][Rr][Ii][Pp][Tt] { BEGIN INSCRIPT; }

<INSCRIPT>"</"[Ss][Cc][Rr][Ii][Pp][Tt]">" {
	BEGIN INITIAL; 
	*tsearch2_yytext=' '; *(tsearch2_yytext+1) = '\0'; 
	token = tsearch2_yytext;
	tokenlen = tsearch2_yyleng;
	return SPACE;
}

"<!--"	{ BEGIN INCOMMENT; }

<INCOMMENT>"-->"	{ 
	BEGIN INITIAL;
	*tsearch2_yytext=' '; *(tsearch2_yytext+1) = '\0'; 
	token = tsearch2_yytext;
	tokenlen = tsearch2_yyleng;
	return SPACE;
}


"<"[\![:alpha:]]	{ BEGIN INTAG; }

"</"[[:alpha:]]	{ BEGIN INTAG; }

<INTAG>"\""	{ BEGIN QINTAG; }

<QINTAG>"\\\""	;

<QINTAG>"\""	{ BEGIN INTAG; }

<INTAG>">"	{ 
	BEGIN INITIAL;
	token = tsearch2_yytext;
	*tsearch2_yytext=' '; 
	token = tsearch2_yytext;
	tokenlen = 1;
	return TAG;
}

<QINTAG,INTAG,INCOMMENT,INSCRIPT>.|\n 	;

\&(quot|amp|nbsp|lt|gt)\;   {
	token = tsearch2_yytext;
	tokenlen = tsearch2_yyleng;
	return HTMLENTITY;
}

\&\#[0-9][0-9]?[0-9]?\; {
	token = tsearch2_yytext;
	tokenlen = tsearch2_yyleng;
	return HTMLENTITY;
}
 
[-_\.[:alnum:]]+@{HOSTNAME}  /* Emails */ { 
	token = tsearch2_yytext; 
	tokenlen = tsearch2_yyleng;
	return EMAIL; 
}

[+-]?[0-9]+(\.[0-9]+)?[eEdD][+-]?[0-9]+  /* float */ 	{ 
	token = tsearch2_yytext; 
	tokenlen = tsearch2_yyleng;
	return SCIENTIFIC; 
}

[0-9]+\.[0-9]+\.[0-9\.]*[0-9] {
	token = tsearch2_yytext;
	tokenlen = tsearch2_yyleng;
	return VERSIONNUMBER;
}

[+-]?[0-9]+\.[0-9]+ {
	token = tsearch2_yytext;
	tokenlen = tsearch2_yyleng;
	return DECIMAL;
}

[+-][0-9]+ { 
	token = tsearch2_yytext; 
	tokenlen = tsearch2_yyleng;
	return SIGNEDINT; 
}

<DELIM,INITIAL>[0-9]+ { 
	token = tsearch2_yytext; 
	tokenlen = tsearch2_yyleng;
	return UNSIGNEDINT; 
}

http"://"        { 
	BEGIN URL; 
	token = tsearch2_yytext;
	tokenlen = tsearch2_yyleng;
	return HTTP;
}

ftp"://"        { 
	BEGIN URL; 
	token = tsearch2_yytext;
	tokenlen = tsearch2_yyleng;
	return HTTP;
}

<URL,INITIAL>{HOSTNAME}[/:]{URI} { 
	BEGIN SERVER;
	if (s) { free(s); s=NULL; } 
	s = strdup( tsearch2_yytext ); 
	tokenlen = tsearch2_yyleng;
	yyless( 0 ); 
	token = s;
	return FURL;
}

<SERVER,URL,INITIAL>{HOSTNAME} {
	token = tsearch2_yytext; 
	tokenlen = tsearch2_yyleng;
	return HOST;
}

<SERVER>[/:]{URI} 	{
	token = tsearch2_yytext;
	tokenlen = tsearch2_yyleng;
	return URI;
}

[[:alnum:]\./_-]+"/"[[:alnum:]\./_-]+ {
	token = tsearch2_yytext;
	tokenlen = tsearch2_yyleng;
	return FILEPATH;
}

({CYRALPHA}+-)+{CYRALPHA}+ /* composite-word */	{
	BEGIN DELIM;
	if (s) { free(s); s=NULL; } 
	s = strdup( tsearch2_yytext );
	tokenlen = tsearch2_yyleng;
	yyless( 0 );
	token = s;
	return CYRHYPHENWORD;
}

([[:alpha:]]+-)+[[:alpha:]]+ /* composite-word */	{
	 BEGIN DELIM;
	if (s) { free(s); s=NULL; } 
	s = strdup( tsearch2_yytext );
	tokenlen = tsearch2_yyleng;
	yyless( 0 );
	token = s;
	return LATHYPHENWORD;
}

({ALNUM}+-)+{ALNUM}+ /* composite-word */	{
	BEGIN DELIM;
	if (s) { free(s); s=NULL; } 
	s = strdup( tsearch2_yytext );
	tokenlen = tsearch2_yyleng;
	yyless( 0 );
	token = s;
	return HYPHENWORD;
}

<DELIM>[0-9]+\.[0-9]+\.[0-9\.]*[0-9] {
	token = tsearch2_yytext;
	tokenlen = tsearch2_yyleng;
	return VERSIONNUMBER;
}

<DELIM>\+?[0-9]+\.[0-9]+ {
	token = tsearch2_yytext;
	tokenlen = tsearch2_yyleng;
	return DECIMAL;
}

<DELIM>{CYRALPHA}+  /* one word in composite-word */	{ 
	token = tsearch2_yytext; 
	tokenlen = tsearch2_yyleng;
	return CYRPARTHYPHENWORD; 
}

<DELIM>[[:alpha:]]+  /* one word in composite-word */	{ 
	token = tsearch2_yytext; 
	tokenlen = tsearch2_yyleng;
	return LATPARTHYPHENWORD; 
}

<DELIM>{ALNUM}+  /* one word in composite-word */	{ 
	token = tsearch2_yytext; 
	tokenlen = tsearch2_yyleng;
	return PARTHYPHENWORD; 
}

<DELIM>-  { 
	token = tsearch2_yytext;
	tokenlen = tsearch2_yyleng;
	return SPACE;
}

<DELIM,SERVER,URL>.|\n /* return in basic state */	{
	BEGIN INITIAL;
	yyless( 0 );
}

{CYRALPHA}+ /* normal word */	{ 
	token = tsearch2_yytext; 
	tokenlen = tsearch2_yyleng;
	return CYRWORD; 
}

[[:alpha:]]+ /* normal word */	{ 
	token = tsearch2_yytext; 
	tokenlen = tsearch2_yyleng;
	return LATWORD; 
}

{ALNUM}+ /* normal word */	{ 
	token = tsearch2_yytext; 
	tokenlen = tsearch2_yyleng;
	return UWORD; 
}

[ \r\n\t]+ {
	token = tsearch2_yytext;
	tokenlen = tsearch2_yyleng;
	return SPACE;
}

. {
	token = tsearch2_yytext;
	tokenlen = tsearch2_yyleng;
	return SPACE;
} 

%%

/* clearing after parsing from string */
285
void tsearch2_end_parse() {
Teodor Sigaev's avatar
Teodor Sigaev committed
286 287 288 289 290 291
	if (s) { free(s); s=NULL; } 
	tsearch2_yy_delete_buffer( buf );
	buf = NULL;
} 

/* start parse from string */
292
void tsearch2_start_parse_str(char* str, int limit) {
Teodor Sigaev's avatar
Teodor Sigaev committed
293
	if (buf) tsearch2_end_parse();
Teodor Sigaev's avatar
Teodor Sigaev committed
294 295 296 297
	buf = tsearch2_yy_scan_bytes( str, limit );
	tsearch2_yy_switch_to_buffer( buf );
	BEGIN INITIAL;
}