summaryrefslogtreecommitdiff
path: root/src/util
diff options
context:
space:
mode:
Diffstat (limited to 'src/util')
-rw-r--r--src/util/regex.c528
-rw-r--r--src/util/regex.h65
-rw-r--r--src/util/shared.c134
-rw-r--r--src/util/shared.h46
4 files changed, 773 insertions, 0 deletions
diff --git a/src/util/regex.c b/src/util/regex.c
new file mode 100644
index 0000000..58b1f54
--- /dev/null
+++ b/src/util/regex.c
@@ -0,0 +1,528 @@
+/*
+ *
+ * Mini regex-module inspired by Rob Pike's regex code described in:
+ *
+ * http://www.cs.princeton.edu/courses/archive/spr09/cos333/beautiful.html
+ *
+ *
+ *
+ * Supports:
+ * ---------
+ * '.' Dot, matches any character
+ * '^' Start anchor, matches beginning of string
+ * '$' End anchor, matches end of string
+ * '*' Asterisk, match zero or more (greedy)
+ * '+' Plus, match one or more (greedy)
+ * '?' Question, match zero or one (non-greedy)
+ * '[abc]' Character class, match if one of {'a', 'b', 'c'}
+ * '[^abc]' Inverted class, match if NOT one of {'a', 'b', 'c'} -- NOTE: feature is currently broken!
+ * '[a-zA-Z]' Character ranges, the character set of the ranges { a-z | A-Z }
+ * '\s' Whitespace, \t \f \r \n \v and spaces
+ * '\S' Non-whitespace
+ * '\w' Alphanumeric, [a-zA-Z0-9_]
+ * '\W' Non-alphanumeric
+ * '\d' Digits, [0-9]
+ * '\D' Non-digits
+ *
+ *
+ */
+
+
+
+#include "regex.h"
+#include <stdio.h>
+#include <ctype.h>
+
+/* Definitions: */
+
+#define MAX_REGEXP_OBJECTS 30 /* Max number of regex symbols in expression. */
+#define MAX_CHAR_CLASS_LEN 40 /* Max length of character-class buffer in. */
+
+
+enum { UNUSED, DOT, BEGIN, END, QUESTIONMARK, STAR, PLUS, CHAR, CHAR_CLASS, INV_CHAR_CLASS, DIGIT, NOT_DIGIT, ALPHA, NOT_ALPHA, WHITESPACE, NOT_WHITESPACE, /* BRANCH */ };
+
+typedef struct regex_t
+{
+ unsigned char type; /* CHAR, STAR, etc. */
+ union
+ {
+ unsigned char ch; /* the character itself */
+ unsigned char* ccl; /* OR a pointer to characters in class */
+ } u;
+} regex_t;
+
+
+
+/* Private function declarations: */
+static int matchpattern(regex_t* pattern, const char* text, int* matchlength);
+static int matchcharclass(char c, const char* str);
+static int matchstar(regex_t p, regex_t* pattern, const char* text, int* matchlength);
+static int matchplus(regex_t p, regex_t* pattern, const char* text, int* matchlength);
+static int matchone(regex_t p, char c);
+static int matchdigit(char c);
+static int matchalpha(char c);
+static int matchwhitespace(char c);
+static int matchmetachar(char c, const char* str);
+static int matchrange(char c, const char* str);
+static int matchdot(char c);
+static int ismetachar(char c);
+
+
+
+/* Public functions: */
+int re_match(const char* pattern, const char* text, int* matchlength)
+{
+ return re_matchp(re_compile(pattern), text, matchlength);
+}
+
+int re_matchp(re_t pattern, const char* text, int* matchlength)
+{
+ *matchlength = 0;
+ if (pattern != 0)
+ {
+ if (pattern[0].type == BEGIN)
+ {
+ return ((matchpattern(&pattern[1], text, matchlength)) ? 0 : -1);
+ }
+ else
+ {
+ int idx = -1;
+
+ do
+ {
+ idx += 1;
+
+ if (matchpattern(pattern, text, matchlength))
+ {
+ if (text[0] == '\0')
+ return -1;
+
+ return idx;
+ }
+ }
+ while (*text++ != '\0');
+ }
+ }
+ return -1;
+}
+
+re_t re_compile(const char* pattern)
+{
+ /* The sizes of the two static arrays below substantiates the static RAM usage of this module.
+ MAX_REGEXP_OBJECTS is the max number of symbols in the expression.
+ MAX_CHAR_CLASS_LEN determines the size of buffer for chars in all char-classes in the expression. */
+ static regex_t re_compiled[MAX_REGEXP_OBJECTS];
+ static unsigned char ccl_buf[MAX_CHAR_CLASS_LEN];
+ int ccl_bufidx = 1;
+
+ char c; /* current char in pattern */
+ int i = 0; /* index into pattern */
+ int j = 0; /* index into re_compiled */
+
+ while (pattern[i] != '\0' && (j+1 < MAX_REGEXP_OBJECTS))
+ {
+ c = pattern[i];
+
+ switch (c)
+ {
+ /* Meta-characters: */
+ case '^': { re_compiled[j].type = BEGIN; } break;
+ case '$': { re_compiled[j].type = END; } break;
+ case '.': { re_compiled[j].type = DOT; } break;
+ case '*': { re_compiled[j].type = STAR; } break;
+ case '+': { re_compiled[j].type = PLUS; } break;
+ case '?': { re_compiled[j].type = QUESTIONMARK; } break;
+/* case '|': { re_compiled[j].type = BRANCH; } break; <-- not working properly */
+
+ /* Escaped character-classes (\s \w ...): */
+ case '\\':
+ {
+ if (pattern[i+1] != '\0')
+ {
+ /* Skip the escape-char '\\' */
+ i += 1;
+ /* ... and check the next */
+ switch (pattern[i])
+ {
+ /* Meta-character: */
+ case 'd': { re_compiled[j].type = DIGIT; } break;
+ case 'D': { re_compiled[j].type = NOT_DIGIT; } break;
+ case 'w': { re_compiled[j].type = ALPHA; } break;
+ case 'W': { re_compiled[j].type = NOT_ALPHA; } break;
+ case 's': { re_compiled[j].type = WHITESPACE; } break;
+ case 'S': { re_compiled[j].type = NOT_WHITESPACE; } break;
+
+ /* Escaped character, e.g. '.' or '$' */
+ default:
+ {
+ re_compiled[j].type = CHAR;
+ re_compiled[j].u.ch = pattern[i];
+ } break;
+ }
+ }
+ /* '\\' as last char in pattern -> invalid regular expression. */
+/*
+ else
+ {
+ re_compiled[j].type = CHAR;
+ re_compiled[j].ch = pattern[i];
+ }
+*/
+ } break;
+
+ /* Character class: */
+ case '[':
+ {
+ /* Remember where the char-buffer starts. */
+ int buf_begin = ccl_bufidx;
+
+ /* Look-ahead to determine if negated */
+ if (pattern[i+1] == '^')
+ {
+ re_compiled[j].type = INV_CHAR_CLASS;
+ i += 1; /* Increment i to avoid including '^' in the char-buffer */
+ if (pattern[i+1] == 0) /* incomplete pattern, missing non-zero char after '^' */
+ {
+ return 0;
+ }
+ }
+ else
+ {
+ re_compiled[j].type = CHAR_CLASS;
+ }
+
+ /* Copy characters inside [..] to buffer */
+ while ( (pattern[++i] != ']')
+ && (pattern[i] != '\0')) /* Missing ] */
+ {
+ if (pattern[i] == '\\')
+ {
+ if (ccl_bufidx >= MAX_CHAR_CLASS_LEN - 1)
+ {
+ //fputs("exceeded internal buffer!\n", stderr);
+ return 0;
+ }
+ if (pattern[i+1] == 0) /* incomplete pattern, missing non-zero char after '\\' */
+ {
+ return 0;
+ }
+ ccl_buf[ccl_bufidx++] = pattern[i++];
+ }
+ else if (ccl_bufidx >= MAX_CHAR_CLASS_LEN)
+ {
+ //fputs("exceeded internal buffer!\n", stderr);
+ return 0;
+ }
+ ccl_buf[ccl_bufidx++] = pattern[i];
+ }
+ if (ccl_bufidx >= MAX_CHAR_CLASS_LEN)
+ {
+ /* Catches cases such as [00000000000000000000000000000000000000][ */
+ //fputs("exceeded internal buffer!\n", stderr);
+ return 0;
+ }
+ /* Null-terminate string end */
+ ccl_buf[ccl_bufidx++] = 0;
+ re_compiled[j].u.ccl = &ccl_buf[buf_begin];
+ } break;
+
+ /* Other characters: */
+ default:
+ {
+ re_compiled[j].type = CHAR;
+ re_compiled[j].u.ch = c;
+ } break;
+ }
+ /* no buffer-out-of-bounds access on invalid patterns - see https://github.com/kokke/tiny-regex-c/commit/1a279e04014b70b0695fba559a7c05d55e6ee90b */
+ if (pattern[i] == 0)
+ {
+ return 0;
+ }
+
+ i += 1;
+ j += 1;
+ }
+ /* 'UNUSED' is a sentinel used to indicate end-of-pattern */
+ re_compiled[j].type = UNUSED;
+
+ return (re_t) re_compiled;
+}
+
+void re_print(regex_t* pattern)
+{
+ const char* types[] = { "UNUSED", "DOT", "BEGIN", "END", "QUESTIONMARK", "STAR", "PLUS", "CHAR", "CHAR_CLASS", "INV_CHAR_CLASS", "DIGIT", "NOT_DIGIT", "ALPHA", "NOT_ALPHA", "WHITESPACE", "NOT_WHITESPACE", "BRANCH" };
+
+ int i;
+ int j;
+ char c;
+ for (i = 0; i < MAX_REGEXP_OBJECTS; ++i)
+ {
+ if (pattern[i].type == UNUSED)
+ {
+ break;
+ }
+
+ printf("type: %s", types[pattern[i].type]);
+ if (pattern[i].type == CHAR_CLASS || pattern[i].type == INV_CHAR_CLASS)
+ {
+ printf(" [");
+ for (j = 0; j < MAX_CHAR_CLASS_LEN; ++j)
+ {
+ c = pattern[i].u.ccl[j];
+ if ((c == '\0') || (c == ']'))
+ {
+ break;
+ }
+ printf("%c", c);
+ }
+ printf("]");
+ }
+ else if (pattern[i].type == CHAR)
+ {
+ printf(" '%c'", pattern[i].u.ch);
+ }
+ printf("\n");
+ }
+}
+
+
+
+/* Private functions: */
+static int matchdigit(char c)
+{
+ return isdigit(c);
+}
+static int matchalpha(char c)
+{
+ return isalpha(c);
+}
+static int matchwhitespace(char c)
+{
+ return isspace(c);
+}
+static int matchalphanum(char c)
+{
+ return ((c == '_') || matchalpha(c) || matchdigit(c));
+}
+static int matchrange(char c, const char* str)
+{
+ return ( (c != '-')
+ && (str[0] != '\0')
+ && (str[0] != '-')
+ && (str[1] == '-')
+ && (str[2] != '\0')
+ && ( (c >= str[0])
+ && (c <= str[2])));
+}
+static int matchdot(char c)
+{
+#if defined(RE_DOT_MATCHES_NEWLINE) && (RE_DOT_MATCHES_NEWLINE == 1)
+ (void)c;
+ return 1;
+#else
+ return c != '\n' && c != '\r';
+#endif
+}
+static int ismetachar(char c)
+{
+ return ((c == 's') || (c == 'S') || (c == 'w') || (c == 'W') || (c == 'd') || (c == 'D'));
+}
+
+static int matchmetachar(char c, const char* str)
+{
+ switch (str[0])
+ {
+ case 'd': return matchdigit(c);
+ case 'D': return !matchdigit(c);
+ case 'w': return matchalphanum(c);
+ case 'W': return !matchalphanum(c);
+ case 's': return matchwhitespace(c);
+ case 'S': return !matchwhitespace(c);
+ default: return (c == str[0]);
+ }
+}
+
+static int matchcharclass(char c, const char* str)
+{
+ do
+ {
+ if (matchrange(c, str))
+ {
+ return 1;
+ }
+ else if (str[0] == '\\')
+ {
+ /* Escape-char: increment str-ptr and match on next char */
+ str += 1;
+ if (matchmetachar(c, str))
+ {
+ return 1;
+ }
+ else if ((c == str[0]) && !ismetachar(c))
+ {
+ return 1;
+ }
+ }
+ else if (c == str[0])
+ {
+ if (c == '-')
+ {
+ return ((str[-1] == '\0') || (str[1] == '\0'));
+ }
+ else
+ {
+ return 1;
+ }
+ }
+ }
+ while (*str++ != '\0');
+
+ return 0;
+}
+
+static int matchone(regex_t p, char c)
+{
+ switch (p.type)
+ {
+ case DOT: return matchdot(c);
+ case CHAR_CLASS: return matchcharclass(c, (const char*)p.u.ccl);
+ case INV_CHAR_CLASS: return !matchcharclass(c, (const char*)p.u.ccl);
+ case DIGIT: return matchdigit(c);
+ case NOT_DIGIT: return !matchdigit(c);
+ case ALPHA: return matchalphanum(c);
+ case NOT_ALPHA: return !matchalphanum(c);
+ case WHITESPACE: return matchwhitespace(c);
+ case NOT_WHITESPACE: return !matchwhitespace(c);
+ default: return (p.u.ch == c);
+ }
+}
+
+static int matchstar(regex_t p, regex_t* pattern, const char* text, int* matchlength)
+{
+ int prelen = *matchlength;
+ const char* prepoint = text;
+ while ((text[0] != '\0') && matchone(p, *text))
+ {
+ text++;
+ (*matchlength)++;
+ }
+ while (text >= prepoint)
+ {
+ if (matchpattern(pattern, text--, matchlength))
+ return 1;
+ (*matchlength)--;
+ }
+
+ *matchlength = prelen;
+ return 0;
+}
+
+static int matchplus(regex_t p, regex_t* pattern, const char* text, int* matchlength)
+{
+ const char* prepoint = text;
+ while ((text[0] != '\0') && matchone(p, *text))
+ {
+ text++;
+ (*matchlength)++;
+ }
+ while (text > prepoint)
+ {
+ if (matchpattern(pattern, text--, matchlength))
+ return 1;
+ (*matchlength)--;
+ }
+
+ return 0;
+}
+
+static int matchquestion(regex_t p, regex_t* pattern, const char* text, int* matchlength)
+{
+ if (p.type == UNUSED)
+ return 1;
+ if (matchpattern(pattern, text, matchlength))
+ return 1;
+ if (*text && matchone(p, *text++))
+ {
+ if (matchpattern(pattern, text, matchlength))
+ {
+ (*matchlength)++;
+ return 1;
+ }
+ }
+ return 0;
+}
+
+
+#if 0
+
+/* Recursive matching */
+static int matchpattern(regex_t* pattern, const char* text, int *matchlength)
+{
+ int pre = *matchlength;
+ if ((pattern[0].type == UNUSED) || (pattern[1].type == QUESTIONMARK))
+ {
+ return matchquestion(pattern[1], &pattern[2], text, matchlength);
+ }
+ else if (pattern[1].type == STAR)
+ {
+ return matchstar(pattern[0], &pattern[2], text, matchlength);
+ }
+ else if (pattern[1].type == PLUS)
+ {
+ return matchplus(pattern[0], &pattern[2], text, matchlength);
+ }
+ else if ((pattern[0].type == END) && pattern[1].type == UNUSED)
+ {
+ return text[0] == '\0';
+ }
+ else if ((text[0] != '\0') && matchone(pattern[0], text[0]))
+ {
+ (*matchlength)++;
+ return matchpattern(&pattern[1], text+1);
+ }
+ else
+ {
+ *matchlength = pre;
+ return 0;
+ }
+}
+
+#else
+
+/* Iterative matching */
+static int matchpattern(regex_t* pattern, const char* text, int* matchlength)
+{
+ int pre = *matchlength;
+ do
+ {
+ if ((pattern[0].type == UNUSED) || (pattern[1].type == QUESTIONMARK))
+ {
+ return matchquestion(pattern[0], &pattern[2], text, matchlength);
+ }
+ else if (pattern[1].type == STAR)
+ {
+ return matchstar(pattern[0], &pattern[2], text, matchlength);
+ }
+ else if (pattern[1].type == PLUS)
+ {
+ return matchplus(pattern[0], &pattern[2], text, matchlength);
+ }
+ else if ((pattern[0].type == END) && pattern[1].type == UNUSED)
+ {
+ return (text[0] == '\0');
+ }
+/* Branching is not working properly
+ else if (pattern[1].type == BRANCH)
+ {
+ return (matchpattern(pattern, text) || matchpattern(&pattern[2], text));
+ }
+*/
+ (*matchlength)++;
+ }
+ while ((text[0] != '\0') && matchone(*pattern++, *text++));
+
+ *matchlength = pre;
+ return 0;
+}
+
+#endif
diff --git a/src/util/regex.h b/src/util/regex.h
new file mode 100644
index 0000000..69facc6
--- /dev/null
+++ b/src/util/regex.h
@@ -0,0 +1,65 @@
+/*
+ *
+ * Mini regex-module inspired by Rob Pike's regex code described in:
+ *
+ * http://www.cs.princeton.edu/courses/archive/spr09/cos333/beautiful.html
+ *
+ *
+ *
+ * Supports:
+ * ---------
+ * '.' Dot, matches any character
+ * '^' Start anchor, matches beginning of string
+ * '$' End anchor, matches end of string
+ * '*' Asterisk, match zero or more (greedy)
+ * '+' Plus, match one or more (greedy)
+ * '?' Question, match zero or one (non-greedy)
+ * '[abc]' Character class, match if one of {'a', 'b', 'c'}
+ * '[^abc]' Inverted class, match if NOT one of {'a', 'b', 'c'} -- NOTE: feature is currently broken!
+ * '[a-zA-Z]' Character ranges, the character set of the ranges { a-z | A-Z }
+ * '\s' Whitespace, \t \f \r \n \v and spaces
+ * '\S' Non-whitespace
+ * '\w' Alphanumeric, [a-zA-Z0-9_]
+ * '\W' Non-alphanumeric
+ * '\d' Digits, [0-9]
+ * '\D' Non-digits
+ *
+ *
+ */
+
+#ifndef _TINY_REGEX_C
+#define _TINY_REGEX_C
+
+
+#ifndef RE_DOT_MATCHES_NEWLINE
+/* Define to 0 if you DON'T want '.' to match '\r' + '\n' */
+#define RE_DOT_MATCHES_NEWLINE 1
+#endif
+
+#ifdef __cplusplus
+extern "C"{
+#endif
+
+
+
+/* Typedef'd pointer to get abstract datatype. */
+typedef struct regex_t* re_t;
+
+
+/* Compile regex string pattern to a regex_t-array. */
+re_t re_compile(const char* pattern);
+
+
+/* Find matches of the compiled pattern inside text. */
+int re_matchp(re_t pattern, const char* text, int* matchlength);
+
+
+/* Find matches of the txt pattern inside text (will compile automatically first). */
+int re_match(const char* pattern, const char* text, int* matchlength);
+
+
+#ifdef __cplusplus
+}
+#endif
+
+#endif /* ifndef _TINY_REGEX_C */
diff --git a/src/util/shared.c b/src/util/shared.c
new file mode 100644
index 0000000..c5c22e9
--- /dev/null
+++ b/src/util/shared.c
@@ -0,0 +1,134 @@
+#include "shared.h"
+
+#include <errno.h>
+#include <stdarg.h>
+#include <stdlib.h>
+#include <string.h>
+#include <time.h>
+#include <sys/stat.h>
+
+void error(const char* format, ...) {
+ va_list list;
+ va_start(list, format);
+
+ vfprintf(stderr, format, list);
+ fprintf(stderr, "\n");
+ exit(EXIT_FAILURE);
+}
+
+FILE* get_file_s(const char* path, const char* type) {
+ struct stat s;
+ if (lstat(path, &s) < 0) {
+ if (type[0] != 'r') goto read;
+ fprintf(stderr, "error: failed to read %s: %s\n", path, strerror(errno));
+ return NULL;
+ }
+ if (S_ISDIR(s.st_mode)) {
+ fprintf(stderr, "error: %s is a directory\n", path);
+ return NULL;
+ }
+
+ FILE* file;
+read:
+ file = fopen(path, type);
+ if (file == NULL) {
+ fprintf(stderr, "error: failed to open file %s: %s\n", path, strerror(errno));
+ }
+ return file;
+}
+
+FILE* get_file(const char* path, const char* type) {
+ if (streql("-", path) && type[0] == 'r') {
+ clearerr(stdin);
+ return stdin;
+ }
+ FILE* file = get_file_s(path, type);
+ if (file == NULL) exit(EXIT_FAILURE);
+ return file;
+}
+
+long int get_number(const char* text) {
+ char* end;
+ long int n = strtol(text, &end, 10);
+ if (text == end) {
+ error("error: %s is not a valid number", text);
+ }
+ return n;
+}
+
+long int get_blkm(const char* text) {
+ char* end;
+ long int n = strtol(text, &end, 10);
+ if (text == end) {
+ error("error: %s is not a valid bkm", text);
+ }
+ if (*end == '\0') return n;
+ switch (*end) {
+ case 'K':
+ case 'k':
+ return n * 1024;
+ case 'B':
+ case 'b':
+ return n * 512;
+ case 'M':
+ case 'm':
+ return n * 1024 * 1204;
+ default:
+ error("error: invalid bkm type %c", *end);
+ }
+ // shouldnt get here anyways
+ return 0;
+}
+
+bool streql(const char* a, const char* b) {
+ if (*a != *b) return false;
+ int n = 0;
+ while (true) {
+ if (*(a+n) != *(b+n)) return false;
+ if (*(a+n) == '\0') return true;
+ ++n;
+ }
+}
+
+bool prefix(const char* pre, const char* str) {
+ return strncmp(pre, str, strlen(pre)) == 0;
+}
+
+static char fs_types[5] = {'K','M','G','T','P'};
+void print_file_size(size_t bytes, char buf[5]) {
+ int index = 0;
+ float next = bytes;
+ while (true) {
+ if (next < 1000) {
+ break;
+ }
+ if (index == 5) {
+ printf("999P");
+ return;
+ };
+ next /= 1024;
+ index++;
+ }
+
+ int n = snprintf(buf, 4, "%u", (int)(next+.5));
+ if (index > 0) {
+ buf[n] = (fs_types[index - 1]);
+ n++;
+ }
+ buf[n] = '\0';
+}
+
+static char* months[12] =
+ {"Jan", "Feb", "Mar", "Apr", "May", "Jun", "Jul", "Aug", "Sep", "Oct", "Nov", "Dec"};
+void print_date_time(time_t mills, char buf[13]) {
+ struct tm* info;
+ info = localtime(&mills);
+ int n = snprintf(buf, 5, "%s ", months[info->tm_mon]);
+
+ if (info->tm_mday < 10) {
+ buf[n] = ' ';
+ n++;
+ }
+
+ snprintf(buf + n, 13 - n, "%d %02d:%02d ", info->tm_mday, info->tm_hour, info->tm_sec);
+}
diff --git a/src/util/shared.h b/src/util/shared.h
new file mode 100644
index 0000000..5e5f4a9
--- /dev/null
+++ b/src/util/shared.h
@@ -0,0 +1,46 @@
+#pragma once
+
+#include <stdio.h>
+#include <stdbool.h>
+#include <time.h>
+
+#define ANSCII "\x1b["
+#define NEXT ";"
+
+#define RESET "0"
+#define BOLD "1"
+
+#define NORMAL "3"
+#define BACKGROUND "4"
+#define HIGHLIGHT "9"
+
+#define BLACK "0"
+#define RED "1"
+#define GREEN "2"
+#define YELLOW "3"
+#define BLUE "4"
+#define MAGENTA "5"
+#define TURQUOISE "6"
+#define WHITE "7"
+
+#define COLOR "m"
+
+enum When {
+ YES,
+ NO,
+ AUTO
+};
+
+__attribute__ ((__format__(printf, 1, 2)))
+void error(const char* format, ...);
+
+FILE* get_file_s(const char* path, const char* type);
+FILE* get_file(const char* path, const char* type);
+long int get_number(const char* text);
+long int get_blkm(const char* text);
+
+bool streql(const char* a, const char* b);
+bool prefix(const char* pre, const char* str);
+
+void print_file_size(size_t bytes, char buf[5]);
+void print_date_time(time_t mills, char buf[13]);
generated by cgit v1.2.3-freya (git 2.51.0) at 2025-09-22 19:31:52 +0000