/* soapcpp2_lex.l Flex/Lex tokenizer. -------------------------------------------------------------------------------- gSOAP XML Web services tools Copyright (C) 2000-2008, Robert van Engelen, Genivia Inc. All Rights Reserved. This part of the software is released under ONE of the following licenses: GPL, the gSOAP public license, OR Genivia's license for commercial use. -------------------------------------------------------------------------------- gSOAP public license. The contents of this file are subject to the gSOAP Public License Version 1.3 (the "License"); you may not use this file except in compliance with the License. You may obtain a copy of the License at http://www.cs.fsu.edu/~engelen/soaplicense.html Software distributed under the License is distributed on an "AS IS" basis, WITHOUT WARRANTY OF ANY KIND, either express or implied. See the License for the specific language governing rights and limitations under the License. The Initial Developer of the Original Code is Robert A. van Engelen. Copyright (C) 2000-2008 Robert A. van Engelen, Genivia inc. All Rights Reserved. -------------------------------------------------------------------------------- GPL license. This program is free software; you can redistribute it and/or modify it under the terms of the GNU General Public License as published by the Free Software Foundation; either version 2 of the License, or (at your option) any later version. This program is distributed in the hope that it will be useful, but WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for more details. You should have received a copy of the GNU General Public License along with this program; if not, write to the Free Software Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA Author contact information: engelen@genivia.com / engelen@acm.org This program is released under the GPL with the additional exemption that compiling, linking, and/or using OpenSSL is allowed. -------------------------------------------------------------------------------- A commercial use license is available from Genivia, Inc., contact@genivia.com -------------------------------------------------------------------------------- */ %{ #include "soapcpp2.h" #ifdef HAVE_CONFIG_H #include "soapcpp2_yacc.h" #else #include "soapcpp2_yacc.tab.h" #endif #ifdef WITH_BISON YYSTYPE yylval; #undef YY_INPUT #define YY_INPUT(buf, result, max_size) \ { \ int c = getc(yyin); \ result = (c == EOF) ? YY_NULL : (buf[0] = c, 1); \ } #endif #ifndef WITH_LEX #define MAX_IMPORT_DEPTH 16 static struct importlist { struct importlist *next; char name[1]; } *importlist = NULL; static char fnstk[MAX_IMPORT_DEPTH][1024]; static int lnstk[MAX_IMPORT_DEPTH]; static char *imstk[MAX_IMPORT_DEPTH]; static YY_BUFFER_STATE instk[MAX_IMPORT_DEPTH]; #endif int imports = 0; char *imported = NULL; static void check_id(const char*); static Token install_id(); static Token install_int(); static Token install_hex(); static Token install_num(); static Token install_chr(); static Token install_str(); static Token install_pragma(); static void directive(), option(); static Token error_chr(); static Token error_str(); static int convchar(int*); static int hexchar(int*); static int octchar(int*); static void module(const char *name, const char *fullname); static void import(const char *file); static int magic(const char *name); %} ws [ \t\v\n\f\r\x1A\xA0] digit [0-9] alpha [a-zA-Z_] id {alpha}({alpha}|{digit}|::|:{alpha})* int {digit}+ hex 0[xX][0-9a-fA-F]+ num {int}(\.{int}([Ee][+-]?{int})?|(\.{int})?[Ee][+-]?{int}) chr '(\\'|[^'\n])*' str \"(\\\"|\\\n|[^"])*\" module #module{ws}+.*\n import #import{ws}+.*\n %x MLCOMMENT %% {ws} { /* skip white space */ } "/*" { BEGIN(MLCOMMENT); } .|\n { } "*/" { BEGIN(INITIAL); } <> { execerror("Unclosed multiline comment at the end of file"); } "//gsoapopt".*\n { option(); } "//gsoap".*\n { directive(); } "//".*\n { /* skip single line comment */ } "+=" { return PA; } "-=" { return NA; } "*=" { return TA; } "/=" { return DA; } "%=" { return MA; } "&=" { return AA; } "^=" { return XA; } "|=" { return OA; } "<<=" { return LA; } ">>=" { return RA; } "||" { return OR; } "&&" { return AN; } "==" { return EQ; } "!=" { return NE; } "<=" { return LE; } ">=" { return GE; } "<<" { return LS; } ">>" { return RS; } "++" { return PP; } "--" { return NN; } "->" { return AR; } [;,:=|^&<>+\-*/%!?~(){}\[\].@] { return yytext[0]; } {id} { return install_id(); } {int} { return install_int(); } {hex} { return install_hex(); } {num} { return install_num(); } {chr} { return install_chr(); } {str} { return install_str(); } {module} { char *s, *t, buf[1024]; s = strchr(yytext, '"'); strcpy(buf, s+1); s = strchr(buf, '"'); *s = '\0'; t = strchr(s+1, '"'); if (t) { t++; s = strchr(t+1, '"'); *s = '\0'; } module(buf, t); } {import} { char *s, buf[1024]; s = strchr(yytext, '"'); if (s) { strcpy(buf, s+1); s = strchr(buf, '"'); *s = '\0'; import(buf); } else lexerror("Invalid import directive"); } #.*\n { return install_pragma(); } '[^'\n]*/\n { return error_chr(); } \"[^"\n]*/\n { return error_str(); } . { lexerror("Skipping unknown symbol"); } <> { /* when Lex complains: remove this line and below */ #ifndef WITH_LEX if (--imports < 0) yyterminate(); else { yy_delete_buffer(YY_CURRENT_BUFFER); yy_switch_to_buffer(instk[imports]); strcpy(filename, fnstk[imports]); yylineno = lnstk[imports]; imported = imstk[imports]; } #endif } %% /* install_id - lookup identifier in symbol table. If found, return token and symbol table entry. If not found, create entry in symbol table and return ID token. */ static Token install_id() { Symbol *p = lookup(yytext); if (!p) { int i, flag = 0; p = install(yytext, ID); /* [_](x|X)(m|M)(l|L)__ is OK */ /* [_](x|X)(m|M)(l|L).* is not OK */ /* .*__(x|X)(m|M)(l|L) is not OK */ /* .*::(x|X)(m|M)(l|L) is not OK */ for (i = 0; i < yyleng; i++) { if ((yytext[i] == '_' && yytext[i+1] == '_') || (yytext[i] == ':' && yytext[i+1] == ':')) { flag = 1; check_id(yytext + i + 2); } } if (!flag && strcmp(yytext, "XML")) check_id(yytext); } yylval.sym = p; return p->token; } /* check_id - check for (x|X)(m|M)(l|L) */ static void check_id(const char *s) { while (*s == '_') s++; if ((s[0] == 'x' || s[0] == 'X') && (s[1] == 'm' || s[1] == 'M') && (s[2] == 'l' || s[2] == 'L')) { sprintf(errbuf, "identifier contains prohibited '%3.3s' sequence: %s", s, yytext); semwarn(errbuf); } } /* install_int - convert digits to integer and return LNG token. */ static Token install_int() { sscanf(yytext, SOAP_ULONG_FORMAT, &yylval.i); return LNG; } /* install_hex - convert hexadecimal digits to integer and return LNG */ static Token install_hex() { sscanf(yytext, SOAP_XLONG_FORMAT, &yylval.i); return LNG; } /* install_num - convert digits to floating point number and return DBL */ static Token install_num() { sscanf(yytext, "%lf", &yylval.r); return DBL; } /* install_chr - convert character constant and return CHR. */ static Token install_chr() { int i = 2; if (yytext[1] == '\\') yylval.c = convchar(&i); else yylval.c = yytext[i-1]; if (yytext[i] != '\'') lexerror("Illegal character constant"); return CHR; } /* install_str - convert and store string in memory. Return STR. */ static Token install_str() { int i, j = 0; yylval.s = emalloc(yyleng-1); /* yyleng = length(yytext) */ for (i = 1; i < yyleng-1; i++) if (yytext[i] == '\\') { if (yytext[++i] != '\n') { yylval.s[j++] = convchar(&i); i--; } } else yylval.s[j++] = yytext[i]; yylval.s[j] = '\0'; return STR; } /* install_pragma - store pragma in string. Return PRAGMA. */ static Token install_pragma() { yylval.s = emalloc(yyleng); /* yyleng = length(yytext) */ strncpy(yylval.s, yytext, strlen(yytext)-1); yylval.s[strlen(yytext)-1] = '\0'; return PRAGMA; } static void directive() { int i, j, k; char *s; Service *sp; Method *m; Data *d; int service; for (i = 7; yytext[i]; i++) if (yytext[i] > 32) break; for (j = i; yytext[j]; j++) if (yytext[j] <= 32) break; if (i == j) return; s = (char*)emalloc(j-i+1); for (k = 0; k < j-i; k++) { s[k] = yytext[k+i]; if (s[k] == '_') s[k] = '-'; } s[k] = '\0'; for (sp = services; sp; sp = sp->next) if (!strcmp(sp->ns, s)) break; if (!sp) { sp = (Service*)emalloc(sizeof(Service)); sp->next = services; sp->ns = s; sp->name = NULL; sp->porttype = NULL; sp->portname = NULL; sp->binding = NULL; sp->definitions = NULL; sp->transport = NULL; sp->URL = NULL; sp->URI = NULL; sp->WSDL = NULL; sp->style = NULL; sp->encoding = NULL; sp->elementForm = NULL; sp->attributeForm = NULL; sp->executable = NULL; sp->import = NULL; sp->documentation = NULL; sp->list = NULL; sp->data = NULL; services = sp; } for (i = j; yytext[i]; i++) if (yytext[i] > 32) break; if (!strncmp(yytext+i, "service", 7) || !strncmp(yytext+i, "schema", 6)) { service = strncmp(yytext+i, "schema", 6); for (i += 7; yytext[i]; i++) if (yytext[i] > 32) break; for (j = i; yytext[j]; j++) if (yytext[j] <= 32) break; for (; yytext[j]; j++) if (yytext[j] > 32) break; for (k = j; yytext[k]; k++) if (yytext[k] <= 32) break; /* if (j == k) return; */ s = (char*)emalloc(k-j+1); strncpy(s, yytext+j, k-j); s[k-j] = '\0'; if (!strncmp(yytext+i, "name:", 5)) { sp->name = s; for (j = k; yytext[j]; j++) if (yytext[j] > 32) break; for (k = j; yytext[k]; k++) if (yytext[k] == 10 || yytext[k] == 13) break; if (j == k) return; s = (char*)emalloc(k-j+1); strncpy(s, yytext+j, k-j); s[k-j] = '\0'; sp->documentation = s; } else if (!strncmp(yytext+i, "type:", 5)) sp->porttype = s; else if (!strncmp(yytext+i, "portType:", 9)) sp->porttype = s; else if (!strncmp(yytext+i, "portName:", 9)) sp->portname = s; else if (!strncmp(yytext+i, "binding:", 8)) sp->binding = s; else if (!strncmp(yytext+i, "definitions:", 12)) sp->definitions = s; else if (!strncmp(yytext+i, "documentation:", 14)) { for (k = j; yytext[k]; k++) if (yytext[k] == 10 || yytext[k] == 13) break; if (j == k) return; s = (char*)emalloc(k-j+1); strncpy(s, yytext+j, k-j); s[k-j] = '\0'; sp->documentation = s; } else if (!strncmp(yytext+i, "transport:", 10)) sp->transport = s; else if (!strncmp(yytext+i, "location:", 9) || !strncmp(yytext+i, "port:", 5)) { sp->URL = s; if (!service) sp->import = s; } else if (!strncmp(yytext+i, "executable:", 11)) sp->executable = s; else if (!strncmp(yytext+i, "namespace:", 10)) { if (service) { if (!sp->URI) sp->URI = s; sp->WSDL = s; } else if (!strcmp(sp->ns, "SOAP-ENV")) { if (vflag) semwarn("option -1 or -2 overrides SOAP-ENV namespace"); else envURI = s; sp->URI = envURI; } else if (!strcmp(sp->ns, "SOAP-ENC")) { if (vflag) semwarn("option -1 or -2 overrides SOAP-ENC namespace"); else encURI = s; sp->URI = encURI = s; } else sp->URI = s; } else if (!strncmp(yytext+i, "form:", 5)) { sp->elementForm = s; sp->attributeForm = s; } else if (!strncmp(yytext+i, "elementForm:", 12)) sp->elementForm = s; else if (!strncmp(yytext+i, "attributeForm:", 14)) sp->attributeForm = s; else if (!strncmp(yytext+i, "import:", 7)) { if (!sp->URI) sp->URI = s; sp->import = s; } else if (!strncmp(yytext+i, "encoding:", 9)) { if (!strcmp(s, "encoded")) sp->encoding = ""; else sp->encoding = s; } else if (!strncmp(yytext+i, "style:", 6)) sp->style = s; else if (!strncmp(yytext+i, "method-style:", 13)) { m = (Method*)emalloc(sizeof(Method)); m->name = s; m->mess = STYLE; m->part = NULL; m->next = sp->list; sp->list = m; for (j = k; yytext[j]; j++) if (yytext[j] > 32) break; for (k = j; yytext[k]; k++) if (yytext[k] == 10 || yytext[k] == 13) break; if (j == k) return; s = (char*)emalloc(k-j+1); strncpy(s, yytext+j, k-j); s[k-j] = '\0'; m->part = s; } else if (!strncmp(yytext+i, "method-encoding:", 16)) { m = (Method*)emalloc(sizeof(Method)); m->name = s; m->mess = ENCODING; m->part = NULL; m->next = sp->list; sp->list = m; for (j = k; yytext[j]; j++) if (yytext[j] > 32) break; for (k = j; yytext[k]; k++) if (yytext[k] == 10 || yytext[k] == 13) break; if (j == k) return; s = (char*)emalloc(k-j+1); strncpy(s, yytext+j, k-j); s[k-j] = '\0'; if (strcmp(s, "encoded")) m->part = s; else m->part = ""; } else if (!strncmp(yytext+i, "method-response-encoding:", 25)) { m = (Method*)emalloc(sizeof(Method)); m->name = s; m->mess = RESPONSE_ENCODING; m->part = NULL; m->next = sp->list; sp->list = m; for (j = k; yytext[j]; j++) if (yytext[j] > 32) break; for (k = j; yytext[k]; k++) if (yytext[k] == 10 || yytext[k] == 13) break; if (j == k) return; s = (char*)emalloc(k-j+1); strncpy(s, yytext+j, k-j); s[k-j] = '\0'; if (strcmp(s, "encoded")) m->part = s; else m->part = ""; } else if (!strncmp(yytext+i, "method-documentation:", 21)) { m = (Method*)emalloc(sizeof(Method)); m->name = s; m->mess = COMMENT; m->part = NULL; m->next = sp->list; sp->list = m; for (j = k; yytext[j]; j++) if (yytext[j] > 32) break; for (k = j; yytext[k]; k++) if (yytext[k] == 10 || yytext[k] == 13) break; if (j == k) return; s = (char*)emalloc(k-j+1); strncpy(s, yytext+j, k-j); s[k-j] = '\0'; m->part = s; } else if (!strncmp(yytext+i, "method-action:", 14)) { m = (Method*)emalloc(sizeof(Method)); m->name = s; m->mess = ACTION; m->part = NULL; m->next = sp->list; sp->list = m; for (j = k; yytext[j]; j++) if (yytext[j] > 32) break; for (k = j; yytext[k]; k++) if (yytext[k] <= 32) break; if (j == k) return; s = (char*)emalloc(k-j+1); strncpy(s, yytext+j, k-j); s[k-j] = '\0'; m->part = s; } else if (!strncmp(yytext+i, "method-mime-type:", 17)) { m = (Method*)emalloc(sizeof(Method)); m->name = s; m->mess = MIMEIN | MIMEOUT; m->part = NULL; m->next = sp->list; sp->list = m; for (j = k; yytext[j]; j++) if (yytext[j] > 32) break; for (k = j; yytext[k]; k++) if (yytext[k] <= 32) break; if (j == k) return; s = (char*)emalloc(k-j+1); strncpy(s, yytext+j, k-j); s[k-j] = '\0'; m->part = s; } else if (!strncmp(yytext+i, "method-input-mime-type:", 23)) { m = (Method*)emalloc(sizeof(Method)); m->name = s; m->mess = MIMEIN; m->part = NULL; m->next = sp->list; sp->list = m; for (j = k; yytext[j]; j++) if (yytext[j] > 32) break; for (k = j; yytext[k]; k++) if (yytext[k] <= 32) break; if (j == k) return; s = (char*)emalloc(k-j+1); strncpy(s, yytext+j, k-j); s[k-j] = '\0'; m->part = s; } else if (!strncmp(yytext+i, "method-output-mime-type:", 24)) { m = (Method*)emalloc(sizeof(Method)); m->name = s; m->mess = MIMEOUT; m->part = NULL; m->next = sp->list; sp->list = m; for (j = k; yytext[j]; j++) if (yytext[j] > 32) break; for (k = j; yytext[k]; k++) if (yytext[k] <= 32) break; if (j == k) return; s = (char*)emalloc(k-j+1); strncpy(s, yytext+j, k-j); s[k-j] = '\0'; m->part = s; } else if (!strncmp(yytext+i, "method-header-part:", 19)) { m = (Method*)emalloc(sizeof(Method)); m->name = s; m->mess = HDRIN | HDROUT; m->part = NULL; m->next = sp->list; sp->list = m; for (j = k; yytext[j]; j++) if (yytext[j] > 32) break; for (k = j; yytext[k]; k++) if (yytext[k] <= 32) break; if (j == k) return; s = (char*)emalloc(k-j+1); strncpy(s, yytext+j, k-j); s[k-j] = '\0'; m->part = s; } else if (!strncmp(yytext+i, "method-input-header-part:", 25)) { m = (Method*)emalloc(sizeof(Method)); m->name = s; m->mess = HDRIN; m->part = NULL; m->next = sp->list; sp->list = m; for (j = k; yytext[j]; j++) if (yytext[j] > 32) break; for (k = j; yytext[k]; k++) if (yytext[k] <= 32) break; if (j == k) return; s = (char*)emalloc(k-j+1); strncpy(s, yytext+j, k-j); s[k-j] = '\0'; m->part = s; } else if (!strncmp(yytext+i, "method-output-header-part:", 26)) { m = (Method*)emalloc(sizeof(Method)); m->name = s; m->mess = HDROUT; m->part = NULL; m->next = sp->list; sp->list = m; for (j = k; yytext[j]; j++) if (yytext[j] > 32) break; for (k = j; yytext[k]; k++) if (yytext[k] <= 32) break; if (j == k) return; s = (char*)emalloc(k-j+1); strncpy(s, yytext+j, k-j); s[k-j] = '\0'; m->part = s; } else if (!strncmp(yytext+i, "method-fault:", 13)) { m = (Method*)emalloc(sizeof(Method)); m->name = s; m->mess = FAULT; m->part = NULL; m->next = sp->list; sp->list = m; for (j = k; yytext[j]; j++) if (yytext[j] > 32) break; for (k = j; yytext[k]; k++) if (yytext[k] <= 32) break; if (j == k) return; s = (char*)emalloc(k-j+1); strncpy(s, yytext+j, k-j); s[k-j] = '\0'; m->part = s; } else if (!strncmp(yytext+i, "type-documentation:", 19)) { d = (Data*)emalloc(sizeof(Data)); d->name = s; d->part = NULL; d->next = sp->data; sp->data = d; for (j = k; yytext[j]; j++) if (yytext[j] > 32) break; for (k = j; yytext[k]; k++) if (yytext[k] == 10 || yytext[k] == 13) break; if (j == k) return; s = (char*)emalloc(k-j+1); strncpy(s, yytext+j, k-j); s[k-j] = '\0'; d->part = s; } else { sprintf(errbuf, "unrecognized gsoap directive: %s", yytext+i); semwarn(errbuf); } } else { sprintf(errbuf, "unrecognized gsoap directive: %s", yytext); semwarn(errbuf); } } static void option() { int i; if (imports) { sprintf(errbuf, "options directive: %s ignored in imported file(s)", yytext); semwarn(errbuf); return; } for (i = 10; yytext[i]; i++) if (yytext[i] > 32) break; for (; yytext[i]; i++) switch (yytext[i]) { case 'c': cflag = 1; break; case 'e': eflag = 1; break; case 'n': nflag = 1; break; case 'l': lflag = 1; break; case 't': tflag = 1; break; case 'w': wflag = 1; break; default: if (yytext[i] <= 32) return; } } /* error_chr - lexical error in character constant. Return character 0 to allow parsing to continue */ static Token error_chr() { lexerror("Ending-' missing in character constant"); yylval.c = '\0'; return CHR; } /* error_str - lexical error in string. Return empty string to allow parsing to continue */ static Token error_str() { lexerror("Ending-\" missing in string"); yylval.s = ""; return STR; } /* Character conversion functions */ static int convchar(int *p) { switch (yytext[(*p)++]) { case 'a': return '\a'; case 'b': return '\b'; case 'f': return '\f'; case 'n': return '\n'; case 'r': return '\r'; case 't': return '\t'; case 'v': return '\v'; case 'x': return hexchar(p); case '0': case '1': case '2': case '3': case '4': case '5': case '6': case '7': (*p)--; return octchar(p); default: return yytext[*p-1]; } } static int hexchar(int *p) { int i, d, c = 0; for (i = 0; isxdigit(d = yytext[*p]) && i < 2; i++) { c = (c << 4) + (d <= '9' ? d - '0' : toupper(d) - '7'); (*p)++; } return c; } static int octchar(int *p) { int i, d, c = 0; for (i = 0; (d = yytext[*p]) >= '0' && d <= '7' && i < 3; i++) { c = (c << 3) + d - '0'; (*p)++; } return c; } static void module(const char *name, const char *fullname) { if (!fullname) fullname = name; if (imports) { Pragma **pp; char *s = emalloc(strlen(fullname)+15); sprintf(s, "#include \"%sH.h\"", fullname); for (pp = &pragmas; *pp; pp = &(*pp)->next) if (!strcmp((*pp)->pragma, s)) break; if (!*pp) { *pp = (Pragma*)emalloc(sizeof(Pragma)); (*pp)->pragma = s; (*pp)->next = NULL; } imported = (char*)emalloc(strlen(fullname)+1); strcpy(imported, fullname); fprintf(stderr, "Importing module '%s'\n\n", fullname); } else { lflag = 1; typeNO = magic(name); prefix = (char*)emalloc(strlen(fullname)+1); strcpy(prefix, fullname); fprintf(stderr, "Compiling module '%s' (magic number = %d)\n\n", fullname, typeNO); } } static int magic(const char *name) { size_t i; int n; if (strlen(name) > 4) semerror("#module name length must not exceed four characters"); n = 0; for (i = 0; i < strlen(name); i++) if (name[i] >= 'a' && name[i] <= 'z') n = 26*n + name[i] - 'a'; else if (name[i] >= 'A' && name[i] <= 'Z') n = 26*n + name[i] - 'A'; else semerror("#module name must be alphabetic and the length must not exceed four characters.\nUse '#module name longname' for longer names."); return 4699*n + 153424; } #ifdef WITH_LEX static void import(const char *file) { execerror("Cannot #import: soapcpp2 not compiled with flex"); } #else static void import(const char *file) { char buf[1024]; struct importlist *p; for (p = importlist; p; p = p->next) if (!strcmp(p->name, file)) return; if (imports >= MAX_IMPORT_DEPTH) execerror("Imports nested too deep"); instk[imports] = YY_CURRENT_BUFFER; strcpy(fnstk[imports], filename); lnstk[imports] = yylineno; imstk[imports] = imported; /* imported = NULL; this is useful to change the semantics of #import to NOT consider non-module imports to be part of the current module */ imports++; if (!(yyin = fopen(file, "r"))) { if (importpath) { char *s, *t; s = importpath; do { t = strstr(s, SOAP_PATHSEP); if (t) { if (t - s >= sizeof(buf)) t = s + sizeof(buf) - 1; strncpy(buf, s, t - s); buf[t - s] = '\0'; s = t + sizeof(SOAP_PATHSEP) - 1; } else { strcpy(buf, s); s = NULL; } strcat(buf, "/"); strcat(buf, file); yyin = fopen(buf, "r"); } while (s && !yyin); } if (!yyin) { sprintf(errbuf, "#import: Cannot open file \"%s\" for reading.\nHint: use option -I (you can define multiple paths separated with '"SOAP_PATHSEP"')", file); execerror(errbuf); } } p = (struct importlist*)malloc(sizeof(struct importlist) + strlen(file)); /* has already + 1 byte size */ strcpy(p->name, file); p->next = importlist; importlist = p; strcpy(filename, file); yy_switch_to_buffer(yy_create_buffer(yyin, YY_BUF_SIZE)); } #endif