This repository has been archived by the owner on Jun 28, 2024. It is now read-only.
generated from dthain/compilerbook-starter-code
-
Notifications
You must be signed in to change notification settings - Fork 0
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
* Add .gitignore * Add Makefile * Add test cases for encoder * Add test script for encoder * Add encoder.c and encoder.h * Add bminor.c
- Loading branch information
Showing
26 changed files
with
375 additions
and
0 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,9 @@ | ||
.vscode | ||
build | ||
cmake-build-debug | ||
tags | ||
|
||
bminor | ||
*.o | ||
|
||
test/**/*.out |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,12 @@ | ||
CC = gcc | ||
.DEFAULT_GOAL = bminor | ||
|
||
encoder.o: encoder.c | ||
$(CC) -c $^ -o $@ | ||
|
||
bminor: bminor.c encoder.o | ||
$(CC) $^ -o $@ | ||
|
||
clean: | ||
rm -f *.o | ||
rm -f bminor |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,55 @@ | ||
#include <stdlib.h> | ||
#include <stdio.h> | ||
#include <string.h> | ||
|
||
#include "encoder.h" | ||
|
||
void usage(int exit_code) | ||
{ | ||
printf("Usage of bminor.\n"); | ||
exit(exit_code); | ||
} | ||
|
||
int main(int argc, char* argv[]) | ||
{ | ||
|
||
if (argc == 1) | ||
usage(1); | ||
|
||
for (int i = 1; i < argc; i++) | ||
{ | ||
if (argv[i][0] == '-') | ||
{ | ||
if (strcmp(argv[i], "--help") == 0) | ||
usage(0); | ||
else if (strcmp(argv[i], "--encode") == 0) | ||
{ | ||
char* filename = argv[++i]; | ||
if (filename) | ||
{ | ||
if (decode(filename) == 0) | ||
{ | ||
// printf("Successfully decoded file %s\n", filename); | ||
return EXIT_SUCCESS; | ||
} else | ||
{ | ||
fprintf(stderr, "Failed to decode file %s\n", filename); | ||
return EXIT_FAILURE; | ||
} | ||
} | ||
else | ||
{ | ||
fprintf(stderr, "Missing filename to be encoded\n"); | ||
return EXIT_FAILURE; | ||
} | ||
} | ||
else | ||
{ | ||
fprintf(stderr, "Unknown option '%s'\n", argv[i]); | ||
usage(1); | ||
} | ||
} | ||
} | ||
|
||
return EXIT_SUCCESS; | ||
} |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,256 @@ | ||
#include <stdlib.h> | ||
#include <stdio.h> | ||
#include <string.h> | ||
|
||
#define MAX_STRING_LEN 255 | ||
|
||
int is_hex(char c) | ||
{ | ||
return c >= '0' && c <= '9' || | ||
c >= 'A' && c <= 'F' || | ||
c >= 'a' && c <= 'f'; | ||
} | ||
|
||
int string_decode(const char* es, char* s) | ||
{ | ||
// printf("Decoding: %s\n", es); | ||
|
||
// Check for start and end quotes | ||
size_t es_len = strlen(es); | ||
if (es_len < 2 || *es != '"' || *(es + es_len - 1) != '"') | ||
{ | ||
fprintf(stderr, "Invalid string: does not start or end with a quote\n"); | ||
return 1; | ||
} | ||
|
||
const char* es_ptr = es + 1; | ||
char* s_ptr = s; | ||
size_t len = 0; | ||
|
||
while (es_ptr < es + es_len - 1) | ||
{ | ||
// Check current length of decoded string | ||
if (len >= MAX_STRING_LEN) | ||
{ | ||
fprintf(stderr, "Invalid string: too long\n"); | ||
return 1; | ||
} | ||
|
||
// Check for printable characters | ||
if (*es_ptr < 32 || *es_ptr > 126) | ||
{ | ||
fprintf(stderr, "Invalid string: invalid character\n"); | ||
return 1; | ||
} | ||
|
||
// Check for escape sequences | ||
if (*es_ptr == '\\') | ||
{ | ||
es_ptr++; | ||
switch (*es_ptr) | ||
{ | ||
case 'a': | ||
*s_ptr = '\a'; | ||
break; | ||
case 'b': | ||
*s_ptr = '\b'; | ||
break; | ||
case 'e': | ||
*s_ptr = 27; | ||
break; | ||
case 'f': | ||
*s_ptr = '\f'; | ||
break; | ||
case 'n': | ||
*s_ptr = '\n'; | ||
break; | ||
case 'r': | ||
*s_ptr = '\r'; | ||
break; | ||
case 't': | ||
*s_ptr = '\t'; | ||
break; | ||
case 'v': | ||
*s_ptr = '\v'; | ||
break; | ||
case '\\': | ||
*s_ptr = '\\'; | ||
break; | ||
case '\'': | ||
*s_ptr = '\''; | ||
break; | ||
case '"': | ||
if (*(es_ptr + 1) == '\0') | ||
{ | ||
fprintf(stderr, "Invalid string: escape sequence at end of string\n"); | ||
return 1; | ||
} | ||
*s_ptr = '"'; | ||
break; | ||
case '0': | ||
es_ptr++; | ||
if (*es_ptr == 'x') | ||
{ | ||
es_ptr++; | ||
if (is_hex(*es_ptr) && is_hex(*(es_ptr + 1))) | ||
{ | ||
char hex[2] = { *es_ptr, *(es_ptr + 1) }; | ||
char val = (char)strtol(hex, NULL, 16); | ||
if (val < 0 || val > 127) | ||
{ | ||
fprintf(stderr, "Invalid string: hex character not in ASCII\n"); | ||
return 1; | ||
} | ||
*s_ptr = val; | ||
es_ptr += 1; | ||
} | ||
else | ||
{ | ||
fprintf(stderr, "Invalid string: invalid hex escape sequence\n"); | ||
return 1; | ||
} | ||
} | ||
break; | ||
default: | ||
fprintf(stderr, "Invalid string: invalid escape sequence\n"); | ||
return 1; | ||
} | ||
es_ptr++; | ||
s_ptr++; | ||
len++; | ||
continue; | ||
} | ||
|
||
*s_ptr = *es_ptr; | ||
|
||
es_ptr++; | ||
s_ptr++; | ||
len++; | ||
} | ||
|
||
// printf("Decoded result: %s\n", s); | ||
|
||
return 0; | ||
} | ||
|
||
int string_encode(const char* s, char* es) | ||
{ | ||
const char* s_ptr = s; | ||
char* es_ptr = es; | ||
|
||
*es_ptr = '"'; | ||
es_ptr++; | ||
|
||
while (*s_ptr != '\0') | ||
{ | ||
// printf("Current: %s\n", s); | ||
// Handle printable characters | ||
if (*s_ptr >= 32 && *s_ptr <= 126) | ||
{ | ||
if (*s_ptr == '"' || *s_ptr == '\\') | ||
{ | ||
*es_ptr = '\\'; | ||
es_ptr++; | ||
} | ||
*es_ptr = *s_ptr; | ||
es_ptr++; | ||
s_ptr++; | ||
continue; | ||
} | ||
|
||
// Handle escape sequences | ||
*es_ptr = '\\'; | ||
es_ptr++; | ||
switch (*s_ptr) | ||
{ | ||
case '\a': | ||
*es_ptr = 'a'; | ||
break; | ||
case '\b': | ||
*es_ptr = 'b'; | ||
break; | ||
case 27: | ||
*es_ptr = 'e'; | ||
break; | ||
case '\f': | ||
*es_ptr = 'f'; | ||
break; | ||
case '\n': | ||
*es_ptr = 'n'; | ||
break; | ||
case '\r': | ||
*es_ptr = 'r'; | ||
break; | ||
case '\t': | ||
*es_ptr = 't'; | ||
break; | ||
case '\v': | ||
*es_ptr = 'v'; | ||
break; | ||
|
||
default: | ||
sprintf(es_ptr, "0x%X", *s_ptr); | ||
es_ptr += 3; | ||
s_ptr++; | ||
break; | ||
} | ||
es_ptr++; | ||
s_ptr++; | ||
// printf("Encoded result: %s\n", es); | ||
} | ||
|
||
*es_ptr = '"'; | ||
es_ptr++; | ||
*es_ptr = '\0'; | ||
return 0; | ||
} | ||
|
||
int decode(char* filename) | ||
{ | ||
FILE* file = fopen(filename, "r"); | ||
if (file == NULL) | ||
{ | ||
printf("Could not open file %s\n", filename); | ||
return 1; | ||
} | ||
|
||
// Find the size of the file | ||
fseek(file, 0, SEEK_END); | ||
long file_size = ftell(file); | ||
if (file_size > (MAX_STRING_LEN * 5 + 2) * sizeof(char)) | ||
{ | ||
fprintf(stderr, "Invalid string: too long\n"); | ||
fclose(file); | ||
return 1; | ||
} | ||
rewind(file); | ||
|
||
// Allocate memory for the file content | ||
// Reserve space for \0 | ||
char* file_content = (char*)malloc(file_size + sizeof(char)); | ||
if (file_content == NULL) | ||
{ | ||
perror("Could not allocate memory"); | ||
fclose(file); | ||
return 1; | ||
} | ||
|
||
// Read the file content into the allocated memory | ||
size_t chars_read = fread(file_content, sizeof(char), file_size, file); | ||
file_content[chars_read] = '\0'; | ||
fclose(file); | ||
|
||
char s[MAX_STRING_LEN + 1] = { 0 }; | ||
|
||
if (string_decode(file_content, s) == 0) | ||
{ | ||
char es[chars_read]; | ||
memset(es, 0, chars_read); | ||
string_encode(s, es); | ||
printf("%s\n", es); | ||
return 0; | ||
} | ||
else | ||
return 1; | ||
|
||
} |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,5 @@ | ||
int string_decode(const char* es, char* s); | ||
|
||
int string_encode(const char* s, char* es); | ||
|
||
int decode(char* filename); |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,19 @@ | ||
#!/bin/sh | ||
|
||
export PATH=$PATH:. | ||
|
||
for testfile in test/encode/good*.bminor; do | ||
if bminor --encode "$testfile" >"$testfile.out"; then | ||
echo "$testfile success (as expected)" | ||
else | ||
echo "$testfile failure (INCORRECT)" | ||
fi | ||
done | ||
|
||
for testfile in test/encode/bad*.bminor; do | ||
if bminor --encode "$testfile" >"$testfile.out"; then | ||
echo "$testfile success (INCORRECT)" | ||
else | ||
echo "$testfile failure (as expected)" | ||
fi | ||
done |
Empty file.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1 @@ | ||
" |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1 @@ | ||
"a \" |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1 @@ | ||
"\\\" |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1 @@ | ||
"\ " |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1 @@ | ||
"\0x" |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1 @@ | ||
" 0123456789 0123456789 0123456789 0123456789 0123456789 0123456789 0123456789 0123456789 0123456789 0123456789 0123456789 0123456789 0123456789 0123456789 0123456789 0123456789 0123456789 0123456789 0123456789 0123456789 0123456789 0123456789 0123456789..." |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1 @@ | ||
"\"\\\a\0xA " |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1 @@ | ||
" \ n \0xAB" |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1 @@ | ||
"\ n" |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1 @@ | ||
"Hello \n World!" |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1 @@ | ||
"\a\b\e\f\n\r\t\v\\\'\"and\0x7F s \0x0Aabs" |
Oops, something went wrong.