aboutsummaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorTom Ryder <tom@sanctum.geek.nz>2019-12-22 19:49:56 +1300
committerTom Ryder <tom@sanctum.geek.nz>2021-09-20 16:05:31 +1200
commit951834e774ae8510cdcdf5dcccc467f4e1b242fb (patch)
tree776e585b4b6ebaa92440ce1a49ec207e36bea22d
parentMake some dense code a little less opaque (diff)
downloadwtf8-951834e774ae8510cdcdf5dcccc467f4e1b242fb.tar.gz
wtf8-951834e774ae8510cdcdf5dcccc467f4e1b242fb.zip
Refactor for legibility
-rw-r--r--wtf8.c63
-rw-r--r--wtf8.h4
2 files changed, 41 insertions, 26 deletions
diff --git a/wtf8.c b/wtf8.c
index 7078ec1..ea8950a 100644
--- a/wtf8.c
+++ b/wtf8.c
@@ -1,31 +1,31 @@
#include "wtf8.h"
/*
- * Check if first two bits of the character are "10", meaning it's a UTF-8
+ * Check if first two bits of the character are "10", meaning it'str a UTF-8
* continuation character
*/
-int is_utf8_cont(unsigned char c) {
- return (c & 0xC0) == 0x80;
+int is_utf8_cont(unsigned char chr) {
+ return (chr & 0xC0) == 0x80;
}
/*
* Print each octet of a string of characters as lowercase hex followed by a
* trailing space, ending with a newline
*/
-void print_octets(char *s) {
- unsigned char c;
+void print_octets(FILE *stream, char *str) {
+ unsigned char chr;
/*
* Iterate through the string, printing each octet, ending with a newline
*/
- while ((c = *s++)) {
+ while ((chr = *str++)) {
char sep;
- sep = is_utf8_cont(c)
+ sep = is_utf8_cont(chr)
? BYTE_SEP
: CHAR_SEP;
- printf("%c%02x", sep, c);
+ fprintf(stream, "%c%02x", sep, chr);
}
- putchar('\n');
+ fputc('\n', stream);
return;
}
@@ -35,37 +35,52 @@ void print_octets(char *s) {
* print_octets(), with each character in line with the end of the octet that
* terminates it, ending with a newline
*/
-void print_characters(char *s) {
-
- /*
- * We need a short counter to find how long each character is
- */
- unsigned char c;
+void print_characters(FILE *stream, char *str) {
/*
* Iterate through the string
*/
- while (*s) {
+ while (*str) {
+
+ /*
+ * We need a short counter to find how long each character is
+ */
+ unsigned char chr;
/*
* Print blanks and increment a counter until we find how long this
* character is
*/
- for (c = 1; is_utf8_cont(s[c]) && c <= UCHAR_MAX; c++)
- printf(" ");
+ for (chr = 1; is_utf8_cont(str[chr]); chr++) {
+
+ /*
+ * Print blanks
+ */
+ fprintf(stream, " ");
+
+ /*
+ * If we've hit UCHAR_MAX, this is probably a perverse
+ * string of bytes for fuzzing or exploitation; bail
+ * out
+ */
+ if (chr == UCHAR_MAX) {
+ fprintf(stderr, "Perverse byte count, bailing\n");
+ exit(1);
+ }
+ }
/*
* Print two spaces, and then the full character
*/
- printf(" ");
- while (c--)
- putchar(*s++);
+ fprintf(stream, " ");
+ while (chr--)
+ fputc(*str++, stream);
}
/*
* End with a newline
*/
- putchar('\n');
+ fputc('\n', stream);
return;
}
@@ -84,8 +99,8 @@ int main(int argc, char **argv) {
* Print the sole argument first as hex octets, then as characters, spaced
* accordingly
*/
- print_octets(argv[1]);
- print_characters(argv[1]);
+ print_octets(stdout, argv[1]);
+ print_characters(stdout, argv[1]);
/*
* Done!
diff --git a/wtf8.h b/wtf8.h
index f6f3de6..e8a40f4 100644
--- a/wtf8.h
+++ b/wtf8.h
@@ -6,5 +6,5 @@
#define CHAR_SEP ' '
int is_utf8_cont(unsigned char);
-void print_octets(char *);
-void print_characters(char *);
+void print_octets(FILE *, char *);
+void print_characters(FILE *, char *);