Lab util: regexfind

Makefile

@@ -145,6 +145,7 @@ UPROGS=\
 	$U/_mkdir\
 	$U/_pingpong\
 	$U/_primes\
+	$U/_regexfind\
 	$U/_rm\
 	$U/_sh\
 	$U/_sleep\

user/regexfind.c

@@ -0,0 +1,112 @@
+#include "kernel/types.h"
+#include "kernel/stat.h"
+#include "kernel/fs.h"
+#include "user/user.h"
+
+int match(char*, char*);
+
+void
+find(char *path, char *pattern)
+{
+  char buf[512], *p;
+  int fd;
+  struct dirent de;
+  struct stat st;
+
+  if ((fd = open(path, 0)) < 0) {
+    fprintf(2, "find: cannot find path %s\n", path);
+    exit(1);
+  }
+
+  if (fstat(fd, &st) < 0) {
+    fprintf(2, "find: cannot stat %s\n", path);
+    close(fd);
+    exit(1);
+  }
+
+  if (st.type != T_DIR) {
+    fprintf(2, "find: %s is not a directory\n", path);
+    close(fd);
+    exit(1);
+  }
+
+  if(strlen(path) + 1 + DIRSIZ + 1 > sizeof buf){
+    fprintf(2, "find: path too long\n");
+    close(fd);
+    exit(1);
+  }
+
+  strcpy(buf, path);
+  p = buf + strlen(buf);
+  *p++ = '/';
+  while (read(fd, &de, sizeof(de)) == sizeof(de)) {
+    if (de.inum == 0 || !strcmp(de.name, ".") || !strcmp(de.name, ".."))
+      continue;
+    memmove(p, de.name, DIRSIZ);
+    p[DIRSIZ] = 0;
+    if (stat(buf, &st) < 0) {
+      fprintf(1, "find: cannot stat %s\n", buf);
+      continue;
+    }
+    if (st.type == T_FILE && match(pattern, de.name)) {
+      fprintf(1, "%s\n", buf);
+    } else if (st.type == T_DIR) {
+      find(buf, pattern);
+    }
+  }
+  close(fd);
+}
+
+int
+main(int argc, char *argv[])
+{
+  if (argc < 2 || argc > 3) {
+    fprintf(2, "Usage: find (path) [file]\n");
+    exit(1);
+  } else if (argc < 3) {
+    find(".", argv[1]);
+  } else {
+    find(argv[1], argv[2]);
+  }
+
+  exit(0);
+}
+
+int matchhere(char*, char*);
+int matchstar(int, char*, char*);
+
+int
+match(char *re, char *text)
+{
+  if(re[0] == '^')
+    return matchhere(re+1, text);
+  do{  // must look at empty string
+    if(matchhere(re, text))
+      return 1;
+  }while(*text++ != '\0');
+  return 0;
+}
+
+// matchhere: search for re at beginning of text
+int matchhere(char *re, char *text)
+{
+  if(re[0] == '\0')
+    return 1;
+  if(re[1] == '*')
+    return matchstar(re[0], re+2, text);
+  if(re[0] == '$' && re[1] == '\0')
+    return *text == '\0';
+  if(*text!='\0' && (re[0]=='.' || re[0]==*text))
+    return matchhere(re+1, text+1);
+  return 0;
+}
+
+// matchstar: search for c*re at beginning of text
+int matchstar(int c, char *re, char *text)
+{
+  do{  // a * matches zero or more instances
+    if(matchhere(re, text))
+      return 1;
+  }while(*text!='\0' && (*text++==c || c=='.'));
+  return 0;
+}