Fixed string literal parsing
This commit is contained in:
Justin J. Meza
parent
2e14ac0b3f
commit
3d68f2b31b
31
lexer.c
31
lexer.c
|
|
@ -259,18 +259,31 @@ LexemeList *scanBuffer(const char *buffer, /**< [in] An array of characters to t
|
|||
&& *(start + len) != '\r'
|
||||
&& *(start + len) != '\n'
|
||||
&& *(start + len) != '"')
|
||||
|| (*(start + len - 1) == ':'
|
||||
&& *(start + len - 2) != '"'))
|
||||
|| (*(start + len) == '"'
|
||||
&& *(start + len - 1) == ':'
|
||||
&& *(start + len - 2) != ':'))
|
||||
len++;
|
||||
if (*(start + len) == '"') len++;
|
||||
/* Make sure this is the end of the token */
|
||||
if (start[len] && !isspace(start[len])
|
||||
&& *(start + len) != ','
|
||||
&& *(start + len) != '!'
|
||||
&& strncmp(start + len, "...", 3)
|
||||
&& strncmp(start + len, "\xE2\x80\xA6", 3)) {
|
||||
fprintf(stderr, "%s:%d: expected token delimiter after string literal\n", fname, line);
|
||||
deleteLexemeList(list);
|
||||
return NULL;
|
||||
}
|
||||
}
|
||||
else {
|
||||
/* Scan for the end of the token */
|
||||
while (start[len] && !isspace(start[len])
|
||||
&& *(start + len) != ','
|
||||
&& *(start + len) != '!'
|
||||
&& strncmp(start + len, "...", 3)
|
||||
&& strncmp(start + len, "\xE2\x80\xA6", 3))
|
||||
len++;
|
||||
}
|
||||
/* Scan for the end of the token */
|
||||
while (start[len] && !isspace(start[len])
|
||||
&& *(start + len) != ','
|
||||
&& *(start + len) != '!'
|
||||
&& strncmp(start + len, "...", 3)
|
||||
&& strncmp(start + len, "\xE2\x80\xA6", 3))
|
||||
len++;
|
||||
temp = malloc(sizeof(char) * (len + 1));
|
||||
if (!temp) {
|
||||
perror("malloc");
|
||||
|
|
|
|||
188
main.c
188
main.c
|
|
@ -97,6 +97,7 @@
|
|||
#include <stdio.h>
|
||||
#include <stdlib.h>
|
||||
#include <unistd.h>
|
||||
#include <getopt.h>
|
||||
|
||||
#include "lexer.h"
|
||||
#include "tokenizer.h"
|
||||
|
|
@ -105,22 +106,25 @@
|
|||
|
||||
#define READSIZE 512
|
||||
|
||||
char *getFileArg(int argc, char **argv, char *vals) {
|
||||
int n;
|
||||
for (n = 1; n < argc; n++) {
|
||||
if (argv[n][0] == '-' && argv[n][1]) {
|
||||
int c;
|
||||
for (c = 0; vals[c] != '\0'; c++) {
|
||||
if (argv[n][1] == vals[c]) {
|
||||
n++;
|
||||
break;
|
||||
}
|
||||
}
|
||||
continue;
|
||||
}
|
||||
else return argv[n];
|
||||
}
|
||||
return NULL;
|
||||
static char *program_name;
|
||||
|
||||
static char *shortopt = "hv";
|
||||
static struct option longopt[] = {
|
||||
{ "help", no_argument, NULL, 'h' },
|
||||
{ "version", no_argument, NULL, 'v' },
|
||||
{ 0, 0, 0, 0 }
|
||||
};
|
||||
|
||||
static void help(void) {
|
||||
fprintf(stderr, "\
|
||||
Usage: %s [FILE] ... \n\
|
||||
Interpret FILE(s) as LOLCODE. Let FILE be '-' for stdin.\n\
|
||||
-h, --help\t\toutput this help\n\
|
||||
-v, --version\t\tprogram version\n", program_name);
|
||||
}
|
||||
|
||||
static void version (char *revision) {
|
||||
fprintf(stderr, "%s %s\n", program_name, revision);
|
||||
}
|
||||
|
||||
int main(int argc, char **argv)
|
||||
|
|
@ -134,74 +138,110 @@ int main(int argc, char **argv)
|
|||
MainNode *node = NULL;
|
||||
char *fname = NULL;
|
||||
FILE *file = NULL;
|
||||
int ch;
|
||||
|
||||
fname = getFileArg(argc, argv, "");
|
||||
if (fname == NULL || fname[0] == '-') {
|
||||
fname = "stdin";
|
||||
file = stdin;
|
||||
}
|
||||
else {
|
||||
file = fopen(fname, "r");
|
||||
}
|
||||
if (!file) {
|
||||
fprintf(stderr, "File does not exist.\n");
|
||||
return 1;
|
||||
}
|
||||
while (!feof(file)) {
|
||||
size += READSIZE;
|
||||
buffer = realloc(buffer, sizeof(char) * size);
|
||||
length += fread((buffer + size) - READSIZE, 1, READSIZE, file);
|
||||
}
|
||||
fclose(file);
|
||||
if (!buffer) return 1;
|
||||
buffer[length] = '\0';
|
||||
char *revision = "v0.9.1";
|
||||
program_name = argv[0];
|
||||
|
||||
/* Remove hash bang line if run as a standalone script */
|
||||
if (buffer[0] == '#' && buffer[1] == '!') {
|
||||
unsigned int n;
|
||||
for (n = 0; buffer[n] != '\n' && buffer[n] != '\r'; n++)
|
||||
buffer[n] = ' ';
|
||||
while ((ch = getopt_long(argc, argv, shortopt, longopt, NULL)) != -1) {
|
||||
switch (ch) {
|
||||
default:
|
||||
fprintf (stderr, "Incorrect option '%c'\n", ch);
|
||||
help();
|
||||
exit(EXIT_FAILURE);
|
||||
|
||||
case 'h':
|
||||
help();
|
||||
exit(EXIT_SUCCESS);
|
||||
break;
|
||||
|
||||
case 'v':
|
||||
version(revision);
|
||||
exit(EXIT_SUCCESS);
|
||||
}
|
||||
}
|
||||
|
||||
/* Remove UTF-8 BOM if present and add it to the output stream (we
|
||||
* assume here that if a BOM is present, the system will also expect
|
||||
* the output to include a BOM). */
|
||||
if (buffer[0] == (char)0xef
|
||||
|| buffer[1] == (char)0xbb
|
||||
|| buffer[2] == (char)0xbf) {
|
||||
buffer[0] = ' ';
|
||||
buffer[1] = ' ';
|
||||
buffer[2] = ' ';
|
||||
printf("%c%c%c", 0xef, 0xbb, 0xbf);
|
||||
}
|
||||
for (; optind < argc; optind++) {
|
||||
size = length = 0;
|
||||
buffer = fname = NULL;
|
||||
lexemes = NULL;
|
||||
tokens = NULL;
|
||||
functab = NULL;
|
||||
node = NULL;
|
||||
file = NULL;
|
||||
|
||||
/* Begin main pipeline */
|
||||
if (!(lexemes = scanBuffer(buffer, length, fname))) {
|
||||
if (!strncmp (argv[optind],"-\0",2)) {
|
||||
file = stdin;
|
||||
fname = "stdin";
|
||||
}
|
||||
else {
|
||||
file = fopen(argv[optind], "r");
|
||||
fname = argv[optind];
|
||||
}
|
||||
|
||||
if (!file) {
|
||||
fprintf(stderr, "File does not exist.\n");
|
||||
return 1;
|
||||
}
|
||||
|
||||
while (!feof(file)) {
|
||||
size += READSIZE;
|
||||
buffer = realloc(buffer, sizeof(char) * size);
|
||||
length += fread((buffer + size) - READSIZE, 1, READSIZE, file);
|
||||
}
|
||||
|
||||
fclose(file);
|
||||
if (!buffer) return 1;
|
||||
buffer[length] = '\0';
|
||||
|
||||
/* Remove hash bang line if run as a standalone script */
|
||||
if (buffer[0] == '#' && buffer[1] == '!') {
|
||||
unsigned int n;
|
||||
for (n = 0; buffer[n] != '\n' && buffer[n] != '\r'; n++)
|
||||
buffer[n] = ' ';
|
||||
}
|
||||
|
||||
/* Remove UTF-8 BOM if present and add it to the output stream (we
|
||||
* assume here that if a BOM is present, the system will also expect
|
||||
* the output to include a BOM). */
|
||||
if (buffer[0] == (char)0xef
|
||||
|| buffer[1] == (char)0xbb
|
||||
|| buffer[2] == (char)0xbf) {
|
||||
buffer[0] = ' ';
|
||||
buffer[1] = ' ';
|
||||
buffer[2] = ' ';
|
||||
printf("%c%c%c", 0xef, 0xbb, 0xbf);
|
||||
}
|
||||
|
||||
/* Begin main pipeline */
|
||||
if (!(lexemes = scanBuffer(buffer, length, fname))) {
|
||||
free(buffer);
|
||||
return 1;
|
||||
}
|
||||
free(buffer);
|
||||
return 1;
|
||||
}
|
||||
free(buffer);
|
||||
if (!(tokens = tokenizeLexemes(lexemes))) {
|
||||
if (!(tokens = tokenizeLexemes(lexemes))) {
|
||||
deleteLexemeList(lexemes);
|
||||
return 1;
|
||||
}
|
||||
deleteLexemeList(lexemes);
|
||||
return 1;
|
||||
}
|
||||
deleteLexemeList(lexemes);
|
||||
if (!(functab = setupFunctionTable(tokens))) {
|
||||
deleteFunctionTable(functab);
|
||||
return 1;
|
||||
}
|
||||
if (!(node = parseMainNode(tokens, functab))) {
|
||||
deleteFunctionTable(functab);
|
||||
if (!(functab = setupFunctionTable(tokens))) {
|
||||
deleteFunctionTable(functab);
|
||||
return 1;
|
||||
}
|
||||
if (!(node = parseMainNode(tokens, functab))) {
|
||||
deleteFunctionTable(functab);
|
||||
deleteTokens(tokens);
|
||||
return 1;
|
||||
}
|
||||
deleteTokens(tokens);
|
||||
return 1;
|
||||
}
|
||||
deleteTokens(tokens);
|
||||
if (interpretMainNode(node)) {
|
||||
if (interpretMainNode(node)) {
|
||||
deleteMainNode(node);
|
||||
return 1;
|
||||
}
|
||||
deleteMainNode(node);
|
||||
return 1;
|
||||
/* End main pipeline */
|
||||
|
||||
}
|
||||
deleteMainNode(node);
|
||||
/* End main pipeline */
|
||||
|
||||
return 0;
|
||||
}
|
||||
|
|
|
|||
Loading…
Reference in New Issue