src/scanner.c

Fri, 03 Jun 2022 20:05:15 +0200

author
Mike Becker <universe@uap-core.de>
date
Fri, 03 Jun 2022 20:05:15 +0200
changeset 66
be2084398c37
parent 61
9c8d768f0244
permissions
-rw-r--r--

new feature: count non-whitespace characters

10
ecf787666f44 refactored sources
Mike Becker <universe@uap-core.de>
parents: 8
diff changeset
1 /*
34
fa9bda32de17 moved src files to src subdirectory and added licence text
Mike Becker <universe@uap-core.de>
parents: 30
diff changeset
2 * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS HEADER.
57
68018eac46c3 adds simple tiny test suite and updates license headers
Mike Becker <universe@uap-core.de>
parents: 54
diff changeset
3 * Copyright 2018 Mike Becker. All rights reserved.
34
fa9bda32de17 moved src files to src subdirectory and added licence text
Mike Becker <universe@uap-core.de>
parents: 30
diff changeset
4 *
fa9bda32de17 moved src files to src subdirectory and added licence text
Mike Becker <universe@uap-core.de>
parents: 30
diff changeset
5 * Redistribution and use in source and binary forms, with or without
fa9bda32de17 moved src files to src subdirectory and added licence text
Mike Becker <universe@uap-core.de>
parents: 30
diff changeset
6 * modification, are permitted provided that the following conditions are met:
fa9bda32de17 moved src files to src subdirectory and added licence text
Mike Becker <universe@uap-core.de>
parents: 30
diff changeset
7 *
fa9bda32de17 moved src files to src subdirectory and added licence text
Mike Becker <universe@uap-core.de>
parents: 30
diff changeset
8 * 1. Redistributions of source code must retain the above copyright
fa9bda32de17 moved src files to src subdirectory and added licence text
Mike Becker <universe@uap-core.de>
parents: 30
diff changeset
9 * notice, this list of conditions and the following disclaimer.
fa9bda32de17 moved src files to src subdirectory and added licence text
Mike Becker <universe@uap-core.de>
parents: 30
diff changeset
10 *
fa9bda32de17 moved src files to src subdirectory and added licence text
Mike Becker <universe@uap-core.de>
parents: 30
diff changeset
11 * 2. Redistributions in binary form must reproduce the above copyright
fa9bda32de17 moved src files to src subdirectory and added licence text
Mike Becker <universe@uap-core.de>
parents: 30
diff changeset
12 * notice, this list of conditions and the following disclaimer in the
fa9bda32de17 moved src files to src subdirectory and added licence text
Mike Becker <universe@uap-core.de>
parents: 30
diff changeset
13 * documentation and/or other materials provided with the distribution.
fa9bda32de17 moved src files to src subdirectory and added licence text
Mike Becker <universe@uap-core.de>
parents: 30
diff changeset
14 *
fa9bda32de17 moved src files to src subdirectory and added licence text
Mike Becker <universe@uap-core.de>
parents: 30
diff changeset
15 * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
fa9bda32de17 moved src files to src subdirectory and added licence text
Mike Becker <universe@uap-core.de>
parents: 30
diff changeset
16 * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
fa9bda32de17 moved src files to src subdirectory and added licence text
Mike Becker <universe@uap-core.de>
parents: 30
diff changeset
17 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
fa9bda32de17 moved src files to src subdirectory and added licence text
Mike Becker <universe@uap-core.de>
parents: 30
diff changeset
18 * DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE
fa9bda32de17 moved src files to src subdirectory and added licence text
Mike Becker <universe@uap-core.de>
parents: 30
diff changeset
19 * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
fa9bda32de17 moved src files to src subdirectory and added licence text
Mike Becker <universe@uap-core.de>
parents: 30
diff changeset
20 * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR
fa9bda32de17 moved src files to src subdirectory and added licence text
Mike Becker <universe@uap-core.de>
parents: 30
diff changeset
21 * SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
fa9bda32de17 moved src files to src subdirectory and added licence text
Mike Becker <universe@uap-core.de>
parents: 30
diff changeset
22 * CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
fa9bda32de17 moved src files to src subdirectory and added licence text
Mike Becker <universe@uap-core.de>
parents: 30
diff changeset
23 * OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
57
68018eac46c3 adds simple tiny test suite and updates license headers
Mike Becker <universe@uap-core.de>
parents: 54
diff changeset
24 * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
10
ecf787666f44 refactored sources
Mike Becker <universe@uap-core.de>
parents: 8
diff changeset
25 */
3
510d6b198dde Moved some functions to functions.c
Mike Becker <universe@uap-core.de>
parents: 1
diff changeset
26
8
28319b20968c encapsulated common operations
Mike Becker <universe@uap-core.de>
parents: 6
diff changeset
27
10
ecf787666f44 refactored sources
Mike Becker <universe@uap-core.de>
parents: 8
diff changeset
28 #include "scanner.h"
21
91e0890464b0 implemented bfile heuristics option + TODO: implement algorithm
Mike Becker <universe@uap-core.de>
parents: 20
diff changeset
29 #include "bfile_heuristics.h"
27
95a958e3de88 added regexp_parser struct and compile function
Mike Becker <universe@uap-core.de>
parents: 25
diff changeset
30 #include "regex_parser.h"
23
778388400f7b encapsulated scanner arguments + enabled optimizer + empty file is no bfile
Mike Becker <universe@uap-core.de>
parents: 22
diff changeset
31 #include <sys/stat.h>
66
be2084398c37 new feature: count non-whitespace characters
Mike Becker <universe@uap-core.de>
parents: 61
diff changeset
32 #include <ctype.h>
3
510d6b198dde Moved some functions to functions.c
Mike Becker <universe@uap-core.de>
parents: 1
diff changeset
33
41
c2e73e175341 replaced direct scanning of directories with a two-step approach (first: create filename list, second: scan)
Mike Becker <universe@uap-core.de>
parents: 40
diff changeset
34 typedef struct filelist filelist_t;
23
778388400f7b encapsulated scanner arguments + enabled optimizer + empty file is no bfile
Mike Becker <universe@uap-core.de>
parents: 22
diff changeset
35
41
c2e73e175341 replaced direct scanning of directories with a two-step approach (first: create filename list, second: scan)
Mike Becker <universe@uap-core.de>
parents: 40
diff changeset
36 struct filelist {
c2e73e175341 replaced direct scanning of directories with a two-step approach (first: create filename list, second: scan)
Mike Becker <universe@uap-core.de>
parents: 40
diff changeset
37 char *displayname;
66
be2084398c37 new feature: count non-whitespace characters
Mike Becker <universe@uap-core.de>
parents: 61
diff changeset
38 unsigned displayname_len;
41
c2e73e175341 replaced direct scanning of directories with a two-step approach (first: create filename list, second: scan)
Mike Becker <universe@uap-core.de>
parents: 40
diff changeset
39 char *filename;
61
9c8d768f0244 adds option to compute individual sums
Mike Becker <universe@uap-core.de>
parents: 60
diff changeset
40 char *ext;
66
be2084398c37 new feature: count non-whitespace characters
Mike Becker <universe@uap-core.de>
parents: 61
diff changeset
41 unsigned st_mode;
41
c2e73e175341 replaced direct scanning of directories with a two-step approach (first: create filename list, second: scan)
Mike Becker <universe@uap-core.de>
parents: 40
diff changeset
42 filelist_t *next;
c2e73e175341 replaced direct scanning of directories with a two-step approach (first: create filename list, second: scan)
Mike Becker <universe@uap-core.de>
parents: 40
diff changeset
43 };
c2e73e175341 replaced direct scanning of directories with a two-step approach (first: create filename list, second: scan)
Mike Becker <universe@uap-core.de>
parents: 40
diff changeset
44
61
9c8d768f0244 adds option to compute individual sums
Mike Becker <universe@uap-core.de>
parents: 60
diff changeset
45 static bool testSuffix(char* filename, string_list_t* list) {
9c8d768f0244 adds option to compute individual sums
Mike Becker <universe@uap-core.de>
parents: 60
diff changeset
46 bool ret = false;
66
be2084398c37 new feature: count non-whitespace characters
Mike Becker <universe@uap-core.de>
parents: 61
diff changeset
47 size_t tokenlen, fnamelen = strlen(filename);
be2084398c37 new feature: count non-whitespace characters
Mike Becker <universe@uap-core.de>
parents: 61
diff changeset
48 for (size_t t = 0 ; t < list->count ; t++) {
61
9c8d768f0244 adds option to compute individual sums
Mike Becker <universe@uap-core.de>
parents: 60
diff changeset
49 tokenlen = strlen(list->items[t]);
9c8d768f0244 adds option to compute individual sums
Mike Becker <universe@uap-core.de>
parents: 60
diff changeset
50 if (fnamelen >= tokenlen && tokenlen > 0) {
9c8d768f0244 adds option to compute individual sums
Mike Becker <universe@uap-core.de>
parents: 60
diff changeset
51 if (strncmp(filename+fnamelen-tokenlen,
9c8d768f0244 adds option to compute individual sums
Mike Becker <universe@uap-core.de>
parents: 60
diff changeset
52 list->items[t], tokenlen) == 0) {
9c8d768f0244 adds option to compute individual sums
Mike Becker <universe@uap-core.de>
parents: 60
diff changeset
53 ret = true;
9c8d768f0244 adds option to compute individual sums
Mike Becker <universe@uap-core.de>
parents: 60
diff changeset
54 break;
9c8d768f0244 adds option to compute individual sums
Mike Becker <universe@uap-core.de>
parents: 60
diff changeset
55 }
9c8d768f0244 adds option to compute individual sums
Mike Becker <universe@uap-core.de>
parents: 60
diff changeset
56 }
9c8d768f0244 adds option to compute individual sums
Mike Becker <universe@uap-core.de>
parents: 60
diff changeset
57 }
9c8d768f0244 adds option to compute individual sums
Mike Becker <universe@uap-core.de>
parents: 60
diff changeset
58 return ret;
9c8d768f0244 adds option to compute individual sums
Mike Becker <universe@uap-core.de>
parents: 60
diff changeset
59 }
9c8d768f0244 adds option to compute individual sums
Mike Becker <universe@uap-core.de>
parents: 60
diff changeset
60
66
be2084398c37 new feature: count non-whitespace characters
Mike Becker <universe@uap-core.de>
parents: 61
diff changeset
61 static void addResultPerExtension(scanresult_ext_t* result,
be2084398c37 new feature: count non-whitespace characters
Mike Becker <universe@uap-core.de>
parents: 61
diff changeset
62 char* ext, unsigned value) {
61
9c8d768f0244 adds option to compute individual sums
Mike Becker <universe@uap-core.de>
parents: 60
diff changeset
63 if (!result) return;
9c8d768f0244 adds option to compute individual sums
Mike Becker <universe@uap-core.de>
parents: 60
diff changeset
64
9c8d768f0244 adds option to compute individual sums
Mike Becker <universe@uap-core.de>
parents: 60
diff changeset
65 if (!ext) ext = "w/o";
9c8d768f0244 adds option to compute individual sums
Mike Becker <universe@uap-core.de>
parents: 60
diff changeset
66
66
be2084398c37 new feature: count non-whitespace characters
Mike Becker <universe@uap-core.de>
parents: 61
diff changeset
67 for (unsigned i = 0 ; i < result->count ; i++) {
61
9c8d768f0244 adds option to compute individual sums
Mike Becker <universe@uap-core.de>
parents: 60
diff changeset
68 if (strcasecmp(result->extensions[i], ext) == 0) {
66
be2084398c37 new feature: count non-whitespace characters
Mike Becker <universe@uap-core.de>
parents: 61
diff changeset
69 result->result[i] += value;
61
9c8d768f0244 adds option to compute individual sums
Mike Becker <universe@uap-core.de>
parents: 60
diff changeset
70 return;
9c8d768f0244 adds option to compute individual sums
Mike Becker <universe@uap-core.de>
parents: 60
diff changeset
71 }
9c8d768f0244 adds option to compute individual sums
Mike Becker <universe@uap-core.de>
parents: 60
diff changeset
72 }
9c8d768f0244 adds option to compute individual sums
Mike Becker <universe@uap-core.de>
parents: 60
diff changeset
73
9c8d768f0244 adds option to compute individual sums
Mike Becker <universe@uap-core.de>
parents: 60
diff changeset
74 if (result->count == result->capacity) {
66
be2084398c37 new feature: count non-whitespace characters
Mike Becker <universe@uap-core.de>
parents: 61
diff changeset
75 unsigned newcap = result->capacity+8;
61
9c8d768f0244 adds option to compute individual sums
Mike Becker <universe@uap-core.de>
parents: 60
diff changeset
76 char** extarr = realloc(result->extensions, newcap*sizeof(char*));
66
be2084398c37 new feature: count non-whitespace characters
Mike Becker <universe@uap-core.de>
parents: 61
diff changeset
77 unsigned* resultarr = realloc(result->result, newcap*sizeof(unsigned));
be2084398c37 new feature: count non-whitespace characters
Mike Becker <universe@uap-core.de>
parents: 61
diff changeset
78 if (!extarr || !resultarr) {
61
9c8d768f0244 adds option to compute individual sums
Mike Becker <universe@uap-core.de>
parents: 60
diff changeset
79 fprintf(stderr, "Memory allocation error.\n");
9c8d768f0244 adds option to compute individual sums
Mike Becker <universe@uap-core.de>
parents: 60
diff changeset
80 abort();
9c8d768f0244 adds option to compute individual sums
Mike Becker <universe@uap-core.de>
parents: 60
diff changeset
81 }
9c8d768f0244 adds option to compute individual sums
Mike Becker <universe@uap-core.de>
parents: 60
diff changeset
82 result->extensions = extarr;
66
be2084398c37 new feature: count non-whitespace characters
Mike Becker <universe@uap-core.de>
parents: 61
diff changeset
83 result->result = resultarr;
61
9c8d768f0244 adds option to compute individual sums
Mike Becker <universe@uap-core.de>
parents: 60
diff changeset
84 result->capacity = newcap;
9c8d768f0244 adds option to compute individual sums
Mike Becker <universe@uap-core.de>
parents: 60
diff changeset
85 }
9c8d768f0244 adds option to compute individual sums
Mike Becker <universe@uap-core.de>
parents: 60
diff changeset
86
9c8d768f0244 adds option to compute individual sums
Mike Becker <universe@uap-core.de>
parents: 60
diff changeset
87 result->extensions[result->count] = strdup(ext);
66
be2084398c37 new feature: count non-whitespace characters
Mike Becker <universe@uap-core.de>
parents: 61
diff changeset
88 result->result[result->count] = value;
61
9c8d768f0244 adds option to compute individual sums
Mike Becker <universe@uap-core.de>
parents: 60
diff changeset
89 result->count++;
9c8d768f0244 adds option to compute individual sums
Mike Becker <universe@uap-core.de>
parents: 60
diff changeset
90 }
9c8d768f0244 adds option to compute individual sums
Mike Becker <universe@uap-core.de>
parents: 60
diff changeset
91
9c8d768f0244 adds option to compute individual sums
Mike Becker <universe@uap-core.de>
parents: 60
diff changeset
92 scanresult_t* new_scanresult_t(settings_t* settings) {
9c8d768f0244 adds option to compute individual sums
Mike Becker <universe@uap-core.de>
parents: 60
diff changeset
93 scanresult_t* result = calloc(1, sizeof(scanresult_t));
9c8d768f0244 adds option to compute individual sums
Mike Becker <universe@uap-core.de>
parents: 60
diff changeset
94 if (settings->individual_sums) {
9c8d768f0244 adds option to compute individual sums
Mike Becker <universe@uap-core.de>
parents: 60
diff changeset
95 result->ext = calloc(1, sizeof(scanresult_ext_t));
9c8d768f0244 adds option to compute individual sums
Mike Becker <universe@uap-core.de>
parents: 60
diff changeset
96 }
9c8d768f0244 adds option to compute individual sums
Mike Becker <universe@uap-core.de>
parents: 60
diff changeset
97 return result;
9c8d768f0244 adds option to compute individual sums
Mike Becker <universe@uap-core.de>
parents: 60
diff changeset
98 }
9c8d768f0244 adds option to compute individual sums
Mike Becker <universe@uap-core.de>
parents: 60
diff changeset
99
9c8d768f0244 adds option to compute individual sums
Mike Becker <universe@uap-core.de>
parents: 60
diff changeset
100 void destroy_scanresult_t(scanresult_t* result) {
9c8d768f0244 adds option to compute individual sums
Mike Becker <universe@uap-core.de>
parents: 60
diff changeset
101 if (result->ext) {
9c8d768f0244 adds option to compute individual sums
Mike Becker <universe@uap-core.de>
parents: 60
diff changeset
102 if (result->ext->count > 0) {
66
be2084398c37 new feature: count non-whitespace characters
Mike Becker <universe@uap-core.de>
parents: 61
diff changeset
103 for (unsigned i = 0 ; i < result->ext->count ; i++) {
61
9c8d768f0244 adds option to compute individual sums
Mike Becker <universe@uap-core.de>
parents: 60
diff changeset
104 free(result->ext->extensions[i]);
9c8d768f0244 adds option to compute individual sums
Mike Becker <universe@uap-core.de>
parents: 60
diff changeset
105 }
9c8d768f0244 adds option to compute individual sums
Mike Becker <universe@uap-core.de>
parents: 60
diff changeset
106 free(result->ext->extensions);
66
be2084398c37 new feature: count non-whitespace characters
Mike Becker <universe@uap-core.de>
parents: 61
diff changeset
107 free(result->ext->result);
61
9c8d768f0244 adds option to compute individual sums
Mike Becker <universe@uap-core.de>
parents: 60
diff changeset
108 }
9c8d768f0244 adds option to compute individual sums
Mike Becker <universe@uap-core.de>
parents: 60
diff changeset
109 free(result->ext);
9c8d768f0244 adds option to compute individual sums
Mike Becker <universe@uap-core.de>
parents: 60
diff changeset
110 }
9c8d768f0244 adds option to compute individual sums
Mike Becker <universe@uap-core.de>
parents: 60
diff changeset
111 free(result);
9c8d768f0244 adds option to compute individual sums
Mike Becker <universe@uap-core.de>
parents: 60
diff changeset
112 }
9c8d768f0244 adds option to compute individual sums
Mike Becker <universe@uap-core.de>
parents: 60
diff changeset
113
66
be2084398c37 new feature: count non-whitespace characters
Mike Becker <universe@uap-core.de>
parents: 61
diff changeset
114 static filelist_t *buildFileList(scanner_t scanner, settings_t* settings) {
61
9c8d768f0244 adds option to compute individual sums
Mike Becker <universe@uap-core.de>
parents: 60
diff changeset
115
66
be2084398c37 new feature: count non-whitespace characters
Mike Becker <universe@uap-core.de>
parents: 61
diff changeset
116 filelist_t* list = NULL;
23
778388400f7b encapsulated scanner arguments + enabled optimizer + empty file is no bfile
Mike Becker <universe@uap-core.de>
parents: 22
diff changeset
117 DIR *dirf;
3
510d6b198dde Moved some functions to functions.c
Mike Becker <universe@uap-core.de>
parents: 1
diff changeset
118 struct dirent *entry;
23
778388400f7b encapsulated scanner arguments + enabled optimizer + empty file is no bfile
Mike Becker <universe@uap-core.de>
parents: 22
diff changeset
119 struct stat statbuf;
41
c2e73e175341 replaced direct scanning of directories with a two-step approach (first: create filename list, second: scan)
Mike Becker <universe@uap-core.de>
parents: 40
diff changeset
120
23
778388400f7b encapsulated scanner arguments + enabled optimizer + empty file is no bfile
Mike Becker <universe@uap-core.de>
parents: 22
diff changeset
121 if ((dirf = opendir(scanner.dir)) == NULL) {
58
bb512754aaf3 fixes error message when directory access fails
Mike Becker <universe@uap-core.de>
parents: 57
diff changeset
122 fprintf(stderr, "%s - ", scanner.dir);
bb512754aaf3 fixes error message when directory access fails
Mike Becker <universe@uap-core.de>
parents: 57
diff changeset
123 perror("Directory access failed");
23
778388400f7b encapsulated scanner arguments + enabled optimizer + empty file is no bfile
Mike Becker <universe@uap-core.de>
parents: 22
diff changeset
124 return 0;
778388400f7b encapsulated scanner arguments + enabled optimizer + empty file is no bfile
Mike Becker <universe@uap-core.de>
parents: 22
diff changeset
125 }
778388400f7b encapsulated scanner arguments + enabled optimizer + empty file is no bfile
Mike Becker <universe@uap-core.de>
parents: 22
diff changeset
126
778388400f7b encapsulated scanner arguments + enabled optimizer + empty file is no bfile
Mike Becker <universe@uap-core.de>
parents: 22
diff changeset
127 while ((entry = readdir(dirf)) != NULL) {
3
510d6b198dde Moved some functions to functions.c
Mike Becker <universe@uap-core.de>
parents: 1
diff changeset
128 if (strcmp(entry->d_name, ".") != 0 && strcmp(entry->d_name, "..") != 0) {
41
c2e73e175341 replaced direct scanning of directories with a two-step approach (first: create filename list, second: scan)
Mike Becker <universe@uap-core.de>
parents: 40
diff changeset
129
c2e73e175341 replaced direct scanning of directories with a two-step approach (first: create filename list, second: scan)
Mike Becker <universe@uap-core.de>
parents: 40
diff changeset
130 /* Create new filelist entry */
c2e73e175341 replaced direct scanning of directories with a two-step approach (first: create filename list, second: scan)
Mike Becker <universe@uap-core.de>
parents: 40
diff changeset
131 filelist_t *newentry = (filelist_t*) malloc(sizeof(filelist_t));
42
0402b9b41b0a file list is now sorted
Mike Becker <universe@uap-core.de>
parents: 41
diff changeset
132 newentry->next = NULL;
41
c2e73e175341 replaced direct scanning of directories with a two-step approach (first: create filename list, second: scan)
Mike Becker <universe@uap-core.de>
parents: 40
diff changeset
133
42
0402b9b41b0a file list is now sorted
Mike Becker <universe@uap-core.de>
parents: 41
diff changeset
134 newentry->displayname_len = strlen(entry->d_name);
0402b9b41b0a file list is now sorted
Mike Becker <universe@uap-core.de>
parents: 41
diff changeset
135 newentry->displayname = (char*) malloc(newentry->displayname_len+1);
0402b9b41b0a file list is now sorted
Mike Becker <universe@uap-core.de>
parents: 41
diff changeset
136 memcpy(newentry->displayname, entry->d_name, newentry->displayname_len);
0402b9b41b0a file list is now sorted
Mike Becker <universe@uap-core.de>
parents: 41
diff changeset
137 newentry->displayname[newentry->displayname_len] = 0;
41
c2e73e175341 replaced direct scanning of directories with a two-step approach (first: create filename list, second: scan)
Mike Becker <universe@uap-core.de>
parents: 40
diff changeset
138
42
0402b9b41b0a file list is now sorted
Mike Becker <universe@uap-core.de>
parents: 41
diff changeset
139 newentry->st_mode = 0;
41
c2e73e175341 replaced direct scanning of directories with a two-step approach (first: create filename list, second: scan)
Mike Becker <universe@uap-core.de>
parents: 40
diff changeset
140
40
5938a9b74e8e improved printing the results and fixed bug where the filename was displayed as an empty string
Mike Becker <universe@uap-core.de>
parents: 36
diff changeset
141 /* Construct absolute pathname string */
41
c2e73e175341 replaced direct scanning of directories with a two-step approach (first: create filename list, second: scan)
Mike Becker <universe@uap-core.de>
parents: 40
diff changeset
142 size_t dirnamelen = strlen(scanner.dir);
42
0402b9b41b0a file list is now sorted
Mike Becker <universe@uap-core.de>
parents: 41
diff changeset
143 char *filename = (char*) malloc(2+dirnamelen+newentry->displayname_len);
41
c2e73e175341 replaced direct scanning of directories with a two-step approach (first: create filename list, second: scan)
Mike Becker <universe@uap-core.de>
parents: 40
diff changeset
144 memcpy(filename, scanner.dir, dirnamelen);
c2e73e175341 replaced direct scanning of directories with a two-step approach (first: create filename list, second: scan)
Mike Becker <universe@uap-core.de>
parents: 40
diff changeset
145 filename[dirnamelen] = settings->fileSeparator;
42
0402b9b41b0a file list is now sorted
Mike Becker <universe@uap-core.de>
parents: 41
diff changeset
146 memcpy(filename+dirnamelen+1, entry->d_name, newentry->displayname_len);
0402b9b41b0a file list is now sorted
Mike Becker <universe@uap-core.de>
parents: 41
diff changeset
147 filename[1+dirnamelen+newentry->displayname_len] = 0;
0402b9b41b0a file list is now sorted
Mike Becker <universe@uap-core.de>
parents: 41
diff changeset
148 newentry->filename = filename;
61
9c8d768f0244 adds option to compute individual sums
Mike Becker <universe@uap-core.de>
parents: 60
diff changeset
149
9c8d768f0244 adds option to compute individual sums
Mike Becker <universe@uap-core.de>
parents: 60
diff changeset
150 /* Obtain file extension */
9c8d768f0244 adds option to compute individual sums
Mike Becker <universe@uap-core.de>
parents: 60
diff changeset
151 newentry->ext = strrchr(newentry->displayname, '.');
14
ee9333c91dda some minor fixes + makefile now injects revisionnumber into cline.h
Mike Becker <universe@uap-core.de>
parents: 10
diff changeset
152
22
4508da679ffb completed binary file heuristics
Mike Becker <universe@uap-core.de>
parents: 21
diff changeset
153 /* Check for subdirectory */
23
778388400f7b encapsulated scanner arguments + enabled optimizer + empty file is no bfile
Mike Becker <universe@uap-core.de>
parents: 22
diff changeset
154 if (stat(filename, &statbuf) == 0) {
42
0402b9b41b0a file list is now sorted
Mike Becker <universe@uap-core.de>
parents: 41
diff changeset
155 newentry->st_mode = statbuf.st_mode;
23
778388400f7b encapsulated scanner arguments + enabled optimizer + empty file is no bfile
Mike Becker <universe@uap-core.de>
parents: 22
diff changeset
156 } else {
778388400f7b encapsulated scanner arguments + enabled optimizer + empty file is no bfile
Mike Becker <universe@uap-core.de>
parents: 22
diff changeset
157 perror(" Error in stat call");
3
510d6b198dde Moved some functions to functions.c
Mike Becker <universe@uap-core.de>
parents: 1
diff changeset
158 continue;
510d6b198dde Moved some functions to functions.c
Mike Becker <universe@uap-core.de>
parents: 1
diff changeset
159 }
42
0402b9b41b0a file list is now sorted
Mike Becker <universe@uap-core.de>
parents: 41
diff changeset
160
0402b9b41b0a file list is now sorted
Mike Becker <universe@uap-core.de>
parents: 41
diff changeset
161 if (list) {
66
be2084398c37 new feature: count non-whitespace characters
Mike Becker <universe@uap-core.de>
parents: 61
diff changeset
162 /* create fake root to have a pointer on the true root */
42
0402b9b41b0a file list is now sorted
Mike Becker <universe@uap-core.de>
parents: 41
diff changeset
163 filelist_t root;
0402b9b41b0a file list is now sorted
Mike Becker <universe@uap-core.de>
parents: 41
diff changeset
164 root.next = list;
0402b9b41b0a file list is now sorted
Mike Becker <universe@uap-core.de>
parents: 41
diff changeset
165 filelist_t *parent = &root;
0402b9b41b0a file list is now sorted
Mike Becker <universe@uap-core.de>
parents: 41
diff changeset
166 while (parent->next &&
0402b9b41b0a file list is now sorted
Mike Becker <universe@uap-core.de>
parents: 41
diff changeset
167 (strcasecmp(parent->next->displayname, newentry->displayname) < 0 ||
0402b9b41b0a file list is now sorted
Mike Becker <universe@uap-core.de>
parents: 41
diff changeset
168 (!S_ISDIR(newentry->st_mode) && S_ISDIR(parent->next->st_mode))
0402b9b41b0a file list is now sorted
Mike Becker <universe@uap-core.de>
parents: 41
diff changeset
169 ) &&
0402b9b41b0a file list is now sorted
Mike Becker <universe@uap-core.de>
parents: 41
diff changeset
170 (!S_ISDIR(newentry->st_mode) || S_ISDIR(parent->next->st_mode))
0402b9b41b0a file list is now sorted
Mike Becker <universe@uap-core.de>
parents: 41
diff changeset
171 ) {
0402b9b41b0a file list is now sorted
Mike Becker <universe@uap-core.de>
parents: 41
diff changeset
172 parent = parent->next;
0402b9b41b0a file list is now sorted
Mike Becker <universe@uap-core.de>
parents: 41
diff changeset
173 }
0402b9b41b0a file list is now sorted
Mike Becker <universe@uap-core.de>
parents: 41
diff changeset
174 newentry->next = parent->next;
0402b9b41b0a file list is now sorted
Mike Becker <universe@uap-core.de>
parents: 41
diff changeset
175 parent->next = newentry;
0402b9b41b0a file list is now sorted
Mike Becker <universe@uap-core.de>
parents: 41
diff changeset
176 list = root.next;
0402b9b41b0a file list is now sorted
Mike Becker <universe@uap-core.de>
parents: 41
diff changeset
177 } else {
0402b9b41b0a file list is now sorted
Mike Becker <universe@uap-core.de>
parents: 41
diff changeset
178 list = newentry;
0402b9b41b0a file list is now sorted
Mike Becker <universe@uap-core.de>
parents: 41
diff changeset
179 }
41
c2e73e175341 replaced direct scanning of directories with a two-step approach (first: create filename list, second: scan)
Mike Becker <universe@uap-core.de>
parents: 40
diff changeset
180 }
c2e73e175341 replaced direct scanning of directories with a two-step approach (first: create filename list, second: scan)
Mike Becker <universe@uap-core.de>
parents: 40
diff changeset
181 }
c2e73e175341 replaced direct scanning of directories with a two-step approach (first: create filename list, second: scan)
Mike Becker <universe@uap-core.de>
parents: 40
diff changeset
182
c2e73e175341 replaced direct scanning of directories with a two-step approach (first: create filename list, second: scan)
Mike Becker <universe@uap-core.de>
parents: 40
diff changeset
183 closedir(dirf);
c2e73e175341 replaced direct scanning of directories with a two-step approach (first: create filename list, second: scan)
Mike Becker <universe@uap-core.de>
parents: 40
diff changeset
184
c2e73e175341 replaced direct scanning of directories with a two-step approach (first: create filename list, second: scan)
Mike Becker <universe@uap-core.de>
parents: 40
diff changeset
185 return list;
c2e73e175341 replaced direct scanning of directories with a two-step approach (first: create filename list, second: scan)
Mike Becker <universe@uap-core.de>
parents: 40
diff changeset
186 }
3
510d6b198dde Moved some functions to functions.c
Mike Becker <universe@uap-core.de>
parents: 1
diff changeset
187
60
69be673a4fd0 preparing changes for individual sum feature
Mike Becker <universe@uap-core.de>
parents: 58
diff changeset
188 void scanDirectory(scanner_t scanner, settings_t* settings,
69be673a4fd0 preparing changes for individual sum feature
Mike Becker <universe@uap-core.de>
parents: 58
diff changeset
189 string_list_t* output, scanresult_t* result) {
41
c2e73e175341 replaced direct scanning of directories with a two-step approach (first: create filename list, second: scan)
Mike Becker <universe@uap-core.de>
parents: 40
diff changeset
190
66
be2084398c37 new feature: count non-whitespace characters
Mike Becker <universe@uap-core.de>
parents: 61
diff changeset
191 result->result = 0;
41
c2e73e175341 replaced direct scanning of directories with a two-step approach (first: create filename list, second: scan)
Mike Becker <universe@uap-core.de>
parents: 40
diff changeset
192 bool bfile;
44
9574a181ec26 line sum per directory now displayed + directories without matching files are no longer displayed when -m is used + new buffering strategy replaces stream hack when -V is used
Mike Becker <universe@uap-core.de>
parents: 43
diff changeset
193 char *outbuf;
66
be2084398c37 new feature: count non-whitespace characters
Mike Becker <universe@uap-core.de>
parents: 61
diff changeset
194 const char *result_type = settings->count_chars ? "chars" : "lines";
41
c2e73e175341 replaced direct scanning of directories with a two-step approach (first: create filename list, second: scan)
Mike Becker <universe@uap-core.de>
parents: 40
diff changeset
195
66
be2084398c37 new feature: count non-whitespace characters
Mike Becker <universe@uap-core.de>
parents: 61
diff changeset
196 filelist_t *filelist = buildFileList(scanner, settings);
41
c2e73e175341 replaced direct scanning of directories with a two-step approach (first: create filename list, second: scan)
Mike Becker <universe@uap-core.de>
parents: 40
diff changeset
197
c2e73e175341 replaced direct scanning of directories with a two-step approach (first: create filename list, second: scan)
Mike Becker <universe@uap-core.de>
parents: 40
diff changeset
198 while (filelist != NULL) {
c2e73e175341 replaced direct scanning of directories with a two-step approach (first: create filename list, second: scan)
Mike Becker <universe@uap-core.de>
parents: 40
diff changeset
199
c2e73e175341 replaced direct scanning of directories with a two-step approach (first: create filename list, second: scan)
Mike Becker <universe@uap-core.de>
parents: 40
diff changeset
200 /* Scan subdirectories */
42
0402b9b41b0a file list is now sorted
Mike Becker <universe@uap-core.de>
parents: 41
diff changeset
201 if (!S_ISREG(filelist->st_mode)) {
44
9574a181ec26 line sum per directory now displayed + directories without matching files are no longer displayed when -m is used + new buffering strategy replaces stream hack when -V is used
Mike Becker <universe@uap-core.de>
parents: 43
diff changeset
202 if (settings->recursive && S_ISDIR(filelist->st_mode)) {
9574a181ec26 line sum per directory now displayed + directories without matching files are no longer displayed when -m is used + new buffering strategy replaces stream hack when -V is used
Mike Becker <universe@uap-core.de>
parents: 43
diff changeset
203 string_list_t *recoutput = new_string_list_t();
60
69be673a4fd0 preparing changes for individual sum feature
Mike Becker <universe@uap-core.de>
parents: 58
diff changeset
204 scanresult_t recresult;
61
9c8d768f0244 adds option to compute individual sums
Mike Becker <universe@uap-core.de>
parents: 60
diff changeset
205 recresult.ext = result->ext;
60
69be673a4fd0 preparing changes for individual sum feature
Mike Becker <universe@uap-core.de>
parents: 58
diff changeset
206 scanDirectory(
44
9574a181ec26 line sum per directory now displayed + directories without matching files are no longer displayed when -m is used + new buffering strategy replaces stream hack when -V is used
Mike Becker <universe@uap-core.de>
parents: 43
diff changeset
207 (scanner_t) {filelist->filename, scanner.spaces+1},
60
69be673a4fd0 preparing changes for individual sum feature
Mike Becker <universe@uap-core.de>
parents: 58
diff changeset
208 settings, recoutput, &recresult);
66
be2084398c37 new feature: count non-whitespace characters
Mike Becker <universe@uap-core.de>
parents: 61
diff changeset
209 result->result += recresult.result;
44
9574a181ec26 line sum per directory now displayed + directories without matching files are no longer displayed when -m is used + new buffering strategy replaces stream hack when -V is used
Mike Becker <universe@uap-core.de>
parents: 43
diff changeset
210 if (!settings->matchesOnly || recoutput->count > 0) {
9574a181ec26 line sum per directory now displayed + directories without matching files are no longer displayed when -m is used + new buffering strategy replaces stream hack when -V is used
Mike Becker <universe@uap-core.de>
parents: 43
diff changeset
211 outbuf = (char*) malloc(81);
66
be2084398c37 new feature: count non-whitespace characters
Mike Becker <universe@uap-core.de>
parents: 61
diff changeset
212 snprintf(outbuf, 81, "%*s/%*s%13u %s\n",
44
9574a181ec26 line sum per directory now displayed + directories without matching files are no longer displayed when -m is used + new buffering strategy replaces stream hack when -V is used
Mike Becker <universe@uap-core.de>
parents: 43
diff changeset
213 filelist->displayname_len+scanner.spaces, filelist->displayname,
60
69be673a4fd0 preparing changes for individual sum feature
Mike Becker <universe@uap-core.de>
parents: 58
diff changeset
214 60-filelist->displayname_len-scanner.spaces-1, "",
66
be2084398c37 new feature: count non-whitespace characters
Mike Becker <universe@uap-core.de>
parents: 61
diff changeset
215 recresult.result, result_type);
44
9574a181ec26 line sum per directory now displayed + directories without matching files are no longer displayed when -m is used + new buffering strategy replaces stream hack when -V is used
Mike Becker <universe@uap-core.de>
parents: 43
diff changeset
216 add_string(output, outbuf);
66
be2084398c37 new feature: count non-whitespace characters
Mike Becker <universe@uap-core.de>
parents: 61
diff changeset
217 for (unsigned i = 0 ; i < recoutput->count ; i++) {
44
9574a181ec26 line sum per directory now displayed + directories without matching files are no longer displayed when -m is used + new buffering strategy replaces stream hack when -V is used
Mike Becker <universe@uap-core.de>
parents: 43
diff changeset
218 add_string(output, recoutput->items[i]);
9574a181ec26 line sum per directory now displayed + directories without matching files are no longer displayed when -m is used + new buffering strategy replaces stream hack when -V is used
Mike Becker <universe@uap-core.de>
parents: 43
diff changeset
219 }
9574a181ec26 line sum per directory now displayed + directories without matching files are no longer displayed when -m is used + new buffering strategy replaces stream hack when -V is used
Mike Becker <universe@uap-core.de>
parents: 43
diff changeset
220 }
9574a181ec26 line sum per directory now displayed + directories without matching files are no longer displayed when -m is used + new buffering strategy replaces stream hack when -V is used
Mike Becker <universe@uap-core.de>
parents: 43
diff changeset
221 destroy_string_list_t(recoutput);
9574a181ec26 line sum per directory now displayed + directories without matching files are no longer displayed when -m is used + new buffering strategy replaces stream hack when -V is used
Mike Becker <universe@uap-core.de>
parents: 43
diff changeset
222 } else {
9574a181ec26 line sum per directory now displayed + directories without matching files are no longer displayed when -m is used + new buffering strategy replaces stream hack when -V is used
Mike Becker <universe@uap-core.de>
parents: 43
diff changeset
223 outbuf = (char*) malloc(81);
66
be2084398c37 new feature: count non-whitespace characters
Mike Becker <universe@uap-core.de>
parents: 61
diff changeset
224 snprintf(outbuf, 81, "%*s\n",
be2084398c37 new feature: count non-whitespace characters
Mike Becker <universe@uap-core.de>
parents: 61
diff changeset
225 filelist->displayname_len+scanner.spaces,
be2084398c37 new feature: count non-whitespace characters
Mike Becker <universe@uap-core.de>
parents: 61
diff changeset
226 filelist->displayname);
44
9574a181ec26 line sum per directory now displayed + directories without matching files are no longer displayed when -m is used + new buffering strategy replaces stream hack when -V is used
Mike Becker <universe@uap-core.de>
parents: 43
diff changeset
227 add_string(output, outbuf);
41
c2e73e175341 replaced direct scanning of directories with a two-step approach (first: create filename list, second: scan)
Mike Becker <universe@uap-core.de>
parents: 40
diff changeset
228 }
c2e73e175341 replaced direct scanning of directories with a two-step approach (first: create filename list, second: scan)
Mike Becker <universe@uap-core.de>
parents: 40
diff changeset
229 } else {
30
d642fdb6745e allow parallel use of -s and -S
Mike Becker <universe@uap-core.de>
parents: 28
diff changeset
230 if ((settings->includeSuffixes->count == 0
41
c2e73e175341 replaced direct scanning of directories with a two-step approach (first: create filename list, second: scan)
Mike Becker <universe@uap-core.de>
parents: 40
diff changeset
231 || testSuffix(filelist->displayname, settings->includeSuffixes))
c2e73e175341 replaced direct scanning of directories with a two-step approach (first: create filename list, second: scan)
Mike Becker <universe@uap-core.de>
parents: 40
diff changeset
232 && !testSuffix(filelist->displayname, settings->excludeSuffixes)) {
c2e73e175341 replaced direct scanning of directories with a two-step approach (first: create filename list, second: scan)
Mike Becker <universe@uap-core.de>
parents: 40
diff changeset
233
66
be2084398c37 new feature: count non-whitespace characters
Mike Becker <universe@uap-core.de>
parents: 61
diff changeset
234 /* Count */
be2084398c37 new feature: count non-whitespace characters
Mike Becker <universe@uap-core.de>
parents: 61
diff changeset
235 unsigned res_value = 0;
25
802c5382f499 Added line buffer (and warning message - there is no regexp parser, though)
Mike Becker <universe@uap-core.de>
parents: 23
diff changeset
236 bfile = false;
802c5382f499 Added line buffer (and warning message - there is no regexp parser, though)
Mike Becker <universe@uap-core.de>
parents: 23
diff changeset
237 bfile_reset(settings->bfileHeuristics);
54
76d46533b9a9 regex parser was not properly reset before each file, sometimes resulting in wrong line counts, when the previous scanned file ended with a match
Mike Becker <universe@uap-core.de>
parents: 48
diff changeset
238 regex_parser_reset(settings->regex);
66
be2084398c37 new feature: count non-whitespace characters
Mike Becker <universe@uap-core.de>
parents: 61
diff changeset
239 char line_buffer[MAX_LINELENGTH];
be2084398c37 new feature: count non-whitespace characters
Mike Becker <universe@uap-core.de>
parents: 61
diff changeset
240 unsigned line_buffer_pos = 0;
25
802c5382f499 Added line buffer (and warning message - there is no regexp parser, though)
Mike Becker <universe@uap-core.de>
parents: 23
diff changeset
241
41
c2e73e175341 replaced direct scanning of directories with a two-step approach (first: create filename list, second: scan)
Mike Becker <universe@uap-core.de>
parents: 40
diff changeset
242 FILE *file = fopen(filelist->filename, "r");
3
510d6b198dde Moved some functions to functions.c
Mike Becker <universe@uap-core.de>
parents: 1
diff changeset
243 if (file == NULL) {
44
9574a181ec26 line sum per directory now displayed + directories without matching files are no longer displayed when -m is used + new buffering strategy replaces stream hack when -V is used
Mike Becker <universe@uap-core.de>
parents: 43
diff changeset
244 outbuf = (char*) malloc(81);
66
be2084398c37 new feature: count non-whitespace characters
Mike Becker <universe@uap-core.de>
parents: 61
diff changeset
245 snprintf(outbuf, 81, "%*s",
be2084398c37 new feature: count non-whitespace characters
Mike Becker <universe@uap-core.de>
parents: 61
diff changeset
246 filelist->displayname_len+scanner.spaces,
be2084398c37 new feature: count non-whitespace characters
Mike Becker <universe@uap-core.de>
parents: 61
diff changeset
247 filelist->displayname);
44
9574a181ec26 line sum per directory now displayed + directories without matching files are no longer displayed when -m is used + new buffering strategy replaces stream hack when -V is used
Mike Becker <universe@uap-core.de>
parents: 43
diff changeset
248 add_string(output, outbuf);
3
510d6b198dde Moved some functions to functions.c
Mike Becker <universe@uap-core.de>
parents: 1
diff changeset
249 perror(" File acces failed");
41
c2e73e175341 replaced direct scanning of directories with a two-step approach (first: create filename list, second: scan)
Mike Becker <universe@uap-core.de>
parents: 40
diff changeset
250 } else {
66
be2084398c37 new feature: count non-whitespace characters
Mike Becker <universe@uap-core.de>
parents: 61
diff changeset
251 int a;
41
c2e73e175341 replaced direct scanning of directories with a two-step approach (first: create filename list, second: scan)
Mike Becker <universe@uap-core.de>
parents: 40
diff changeset
252 do {
c2e73e175341 replaced direct scanning of directories with a two-step approach (first: create filename list, second: scan)
Mike Becker <universe@uap-core.de>
parents: 40
diff changeset
253 a = fgetc(file);
c2e73e175341 replaced direct scanning of directories with a two-step approach (first: create filename list, second: scan)
Mike Becker <universe@uap-core.de>
parents: 40
diff changeset
254
c2e73e175341 replaced direct scanning of directories with a two-step approach (first: create filename list, second: scan)
Mike Becker <universe@uap-core.de>
parents: 40
diff changeset
255 bfile = bfile_check(settings->bfileHeuristics, a);
3
510d6b198dde Moved some functions to functions.c
Mike Becker <universe@uap-core.de>
parents: 1
diff changeset
256
66
be2084398c37 new feature: count non-whitespace characters
Mike Becker <universe@uap-core.de>
parents: 61
diff changeset
257 /* ignore carriage return completely */
be2084398c37 new feature: count non-whitespace characters
Mike Becker <universe@uap-core.de>
parents: 61
diff changeset
258 if (a == 13) continue;
be2084398c37 new feature: count non-whitespace characters
Mike Becker <universe@uap-core.de>
parents: 61
diff changeset
259
41
c2e73e175341 replaced direct scanning of directories with a two-step approach (first: create filename list, second: scan)
Mike Becker <universe@uap-core.de>
parents: 40
diff changeset
260 if (a == 10 || a == EOF) {
66
be2084398c37 new feature: count non-whitespace characters
Mike Becker <universe@uap-core.de>
parents: 61
diff changeset
261 line_buffer[line_buffer_pos] = 0;
41
c2e73e175341 replaced direct scanning of directories with a two-step approach (first: create filename list, second: scan)
Mike Becker <universe@uap-core.de>
parents: 40
diff changeset
262 if (regex_parser_do(settings->regex, line_buffer) == 0) {
66
be2084398c37 new feature: count non-whitespace characters
Mike Becker <universe@uap-core.de>
parents: 61
diff changeset
263 /* Subtract excluded lines/chars when matching has finished */
41
c2e73e175341 replaced direct scanning of directories with a two-step approach (first: create filename list, second: scan)
Mike Becker <universe@uap-core.de>
parents: 40
diff changeset
264 if (!regex_parser_matching(settings->regex)) {
66
be2084398c37 new feature: count non-whitespace characters
Mike Becker <universe@uap-core.de>
parents: 61
diff changeset
265 res_value -= settings->regex->matched_counted;
41
c2e73e175341 replaced direct scanning of directories with a two-step approach (first: create filename list, second: scan)
Mike Becker <universe@uap-core.de>
parents: 40
diff changeset
266 }
c2e73e175341 replaced direct scanning of directories with a two-step approach (first: create filename list, second: scan)
Mike Becker <universe@uap-core.de>
parents: 40
diff changeset
267 }
21
91e0890464b0 implemented bfile heuristics option + TODO: implement algorithm
Mike Becker <universe@uap-core.de>
parents: 20
diff changeset
268
66
be2084398c37 new feature: count non-whitespace characters
Mike Becker <universe@uap-core.de>
parents: 61
diff changeset
269 if (settings->count_chars) {
be2084398c37 new feature: count non-whitespace characters
Mike Becker <universe@uap-core.de>
parents: 61
diff changeset
270 for (size_t i = 0 ; i < line_buffer_pos ; i++) {
be2084398c37 new feature: count non-whitespace characters
Mike Becker <universe@uap-core.de>
parents: 61
diff changeset
271 if (!isspace(line_buffer[i])) res_value++;
be2084398c37 new feature: count non-whitespace characters
Mike Becker <universe@uap-core.de>
parents: 61
diff changeset
272 }
be2084398c37 new feature: count non-whitespace characters
Mike Becker <universe@uap-core.de>
parents: 61
diff changeset
273 } else {
be2084398c37 new feature: count non-whitespace characters
Mike Becker <universe@uap-core.de>
parents: 61
diff changeset
274 res_value++;
be2084398c37 new feature: count non-whitespace characters
Mike Becker <universe@uap-core.de>
parents: 61
diff changeset
275 }
be2084398c37 new feature: count non-whitespace characters
Mike Becker <universe@uap-core.de>
parents: 61
diff changeset
276 line_buffer_pos = 0;
41
c2e73e175341 replaced direct scanning of directories with a two-step approach (first: create filename list, second: scan)
Mike Becker <universe@uap-core.de>
parents: 40
diff changeset
277 } else {
66
be2084398c37 new feature: count non-whitespace characters
Mike Becker <universe@uap-core.de>
parents: 61
diff changeset
278 if (line_buffer_pos < MAX_LINELENGTH) {
be2084398c37 new feature: count non-whitespace characters
Mike Becker <universe@uap-core.de>
parents: 61
diff changeset
279 line_buffer[line_buffer_pos] = (char) a;
be2084398c37 new feature: count non-whitespace characters
Mike Becker <universe@uap-core.de>
parents: 61
diff changeset
280 line_buffer_pos++;
41
c2e73e175341 replaced direct scanning of directories with a two-step approach (first: create filename list, second: scan)
Mike Becker <universe@uap-core.de>
parents: 40
diff changeset
281 } else {
66
be2084398c37 new feature: count non-whitespace characters
Mike Becker <universe@uap-core.de>
parents: 61
diff changeset
282 line_buffer[line_buffer_pos - 1] = 0;
41
c2e73e175341 replaced direct scanning of directories with a two-step approach (first: create filename list, second: scan)
Mike Becker <universe@uap-core.de>
parents: 40
diff changeset
283 settings->confusing_lnlen = true;
28
72a98cbcb9f1 added regex parser
Mike Becker <universe@uap-core.de>
parents: 27
diff changeset
284 }
72a98cbcb9f1 added regex parser
Mike Becker <universe@uap-core.de>
parents: 27
diff changeset
285 }
41
c2e73e175341 replaced direct scanning of directories with a two-step approach (first: create filename list, second: scan)
Mike Becker <universe@uap-core.de>
parents: 40
diff changeset
286 } while (!bfile && a != EOF);
c2e73e175341 replaced direct scanning of directories with a two-step approach (first: create filename list, second: scan)
Mike Becker <universe@uap-core.de>
parents: 40
diff changeset
287 fclose(file);
25
802c5382f499 Added line buffer (and warning message - there is no regexp parser, though)
Mike Becker <universe@uap-core.de>
parents: 23
diff changeset
288
41
c2e73e175341 replaced direct scanning of directories with a two-step approach (first: create filename list, second: scan)
Mike Becker <universe@uap-core.de>
parents: 40
diff changeset
289 /* Print and sum line count */
c2e73e175341 replaced direct scanning of directories with a two-step approach (first: create filename list, second: scan)
Mike Becker <universe@uap-core.de>
parents: 40
diff changeset
290 if (bfile) {
c2e73e175341 replaced direct scanning of directories with a two-step approach (first: create filename list, second: scan)
Mike Becker <universe@uap-core.de>
parents: 40
diff changeset
291 if (!settings->matchesOnly) {
44
9574a181ec26 line sum per directory now displayed + directories without matching files are no longer displayed when -m is used + new buffering strategy replaces stream hack when -V is used
Mike Becker <universe@uap-core.de>
parents: 43
diff changeset
292 outbuf = (char*) malloc(81);
9574a181ec26 line sum per directory now displayed + directories without matching files are no longer displayed when -m is used + new buffering strategy replaces stream hack when -V is used
Mike Becker <universe@uap-core.de>
parents: 43
diff changeset
293 snprintf(outbuf, 81,
9574a181ec26 line sum per directory now displayed + directories without matching files are no longer displayed when -m is used + new buffering strategy replaces stream hack when -V is used
Mike Becker <universe@uap-core.de>
parents: 43
diff changeset
294 "%*s%*s%19s\n", filelist->displayname_len+scanner.spaces,
41
c2e73e175341 replaced direct scanning of directories with a two-step approach (first: create filename list, second: scan)
Mike Becker <universe@uap-core.de>
parents: 40
diff changeset
295 filelist->displayname,
c2e73e175341 replaced direct scanning of directories with a two-step approach (first: create filename list, second: scan)
Mike Becker <universe@uap-core.de>
parents: 40
diff changeset
296 60-filelist->displayname_len-scanner.spaces, "", "binary");
44
9574a181ec26 line sum per directory now displayed + directories without matching files are no longer displayed when -m is used + new buffering strategy replaces stream hack when -V is used
Mike Becker <universe@uap-core.de>
parents: 43
diff changeset
297 add_string(output, outbuf);
41
c2e73e175341 replaced direct scanning of directories with a two-step approach (first: create filename list, second: scan)
Mike Becker <universe@uap-core.de>
parents: 40
diff changeset
298 }
25
802c5382f499 Added line buffer (and warning message - there is no regexp parser, though)
Mike Becker <universe@uap-core.de>
parents: 23
diff changeset
299 } else {
66
be2084398c37 new feature: count non-whitespace characters
Mike Becker <universe@uap-core.de>
parents: 61
diff changeset
300 addResultPerExtension(result->ext, filelist->ext, res_value);
be2084398c37 new feature: count non-whitespace characters
Mike Becker <universe@uap-core.de>
parents: 61
diff changeset
301 result->result += res_value;
44
9574a181ec26 line sum per directory now displayed + directories without matching files are no longer displayed when -m is used + new buffering strategy replaces stream hack when -V is used
Mike Becker <universe@uap-core.de>
parents: 43
diff changeset
302 outbuf = (char*) malloc(81);
66
be2084398c37 new feature: count non-whitespace characters
Mike Becker <universe@uap-core.de>
parents: 61
diff changeset
303 snprintf(outbuf, 81, "%*s%*s%13u %s\n",
be2084398c37 new feature: count non-whitespace characters
Mike Becker <universe@uap-core.de>
parents: 61
diff changeset
304 filelist->displayname_len+scanner.spaces,
be2084398c37 new feature: count non-whitespace characters
Mike Becker <universe@uap-core.de>
parents: 61
diff changeset
305 filelist->displayname,
be2084398c37 new feature: count non-whitespace characters
Mike Becker <universe@uap-core.de>
parents: 61
diff changeset
306 60-filelist->displayname_len-scanner.spaces,
be2084398c37 new feature: count non-whitespace characters
Mike Becker <universe@uap-core.de>
parents: 61
diff changeset
307 "",
be2084398c37 new feature: count non-whitespace characters
Mike Becker <universe@uap-core.de>
parents: 61
diff changeset
308 res_value,
be2084398c37 new feature: count non-whitespace characters
Mike Becker <universe@uap-core.de>
parents: 61
diff changeset
309 result_type
be2084398c37 new feature: count non-whitespace characters
Mike Becker <universe@uap-core.de>
parents: 61
diff changeset
310 );
44
9574a181ec26 line sum per directory now displayed + directories without matching files are no longer displayed when -m is used + new buffering strategy replaces stream hack when -V is used
Mike Becker <universe@uap-core.de>
parents: 43
diff changeset
311 add_string(output, outbuf);
3
510d6b198dde Moved some functions to functions.c
Mike Becker <universe@uap-core.de>
parents: 1
diff changeset
312 }
21
91e0890464b0 implemented bfile heuristics option + TODO: implement algorithm
Mike Becker <universe@uap-core.de>
parents: 20
diff changeset
313 }
16
bc9a0fefd892 fixed makefile to run safely on compile errors + added -V option to cline
Mike Becker <universe@uap-core.de>
parents: 14
diff changeset
314 } else {
3
510d6b198dde Moved some functions to functions.c
Mike Becker <universe@uap-core.de>
parents: 1
diff changeset
315 if (!settings->matchesOnly) {
22
4508da679ffb completed binary file heuristics
Mike Becker <universe@uap-core.de>
parents: 21
diff changeset
316 /* Print hint */
44
9574a181ec26 line sum per directory now displayed + directories without matching files are no longer displayed when -m is used + new buffering strategy replaces stream hack when -V is used
Mike Becker <universe@uap-core.de>
parents: 43
diff changeset
317 outbuf = (char*) malloc(81);
9574a181ec26 line sum per directory now displayed + directories without matching files are no longer displayed when -m is used + new buffering strategy replaces stream hack when -V is used
Mike Becker <universe@uap-core.de>
parents: 43
diff changeset
318 snprintf(outbuf, 81, "%*s%*s%19s\n",
41
c2e73e175341 replaced direct scanning of directories with a two-step approach (first: create filename list, second: scan)
Mike Becker <universe@uap-core.de>
parents: 40
diff changeset
319 filelist->displayname_len+scanner.spaces, filelist->displayname,
c2e73e175341 replaced direct scanning of directories with a two-step approach (first: create filename list, second: scan)
Mike Becker <universe@uap-core.de>
parents: 40
diff changeset
320 60-filelist->displayname_len-scanner.spaces, "", "no match");
44
9574a181ec26 line sum per directory now displayed + directories without matching files are no longer displayed when -m is used + new buffering strategy replaces stream hack when -V is used
Mike Becker <universe@uap-core.de>
parents: 43
diff changeset
321 add_string(output, outbuf);
3
510d6b198dde Moved some functions to functions.c
Mike Becker <universe@uap-core.de>
parents: 1
diff changeset
322 }
510d6b198dde Moved some functions to functions.c
Mike Becker <universe@uap-core.de>
parents: 1
diff changeset
323 }
510d6b198dde Moved some functions to functions.c
Mike Becker <universe@uap-core.de>
parents: 1
diff changeset
324 }
41
c2e73e175341 replaced direct scanning of directories with a two-step approach (first: create filename list, second: scan)
Mike Becker <universe@uap-core.de>
parents: 40
diff changeset
325
c2e73e175341 replaced direct scanning of directories with a two-step approach (first: create filename list, second: scan)
Mike Becker <universe@uap-core.de>
parents: 40
diff changeset
326 free(filelist->filename);
c2e73e175341 replaced direct scanning of directories with a two-step approach (first: create filename list, second: scan)
Mike Becker <universe@uap-core.de>
parents: 40
diff changeset
327 free(filelist->displayname);
c2e73e175341 replaced direct scanning of directories with a two-step approach (first: create filename list, second: scan)
Mike Becker <universe@uap-core.de>
parents: 40
diff changeset
328 filelist_t *freethis = filelist;
c2e73e175341 replaced direct scanning of directories with a two-step approach (first: create filename list, second: scan)
Mike Becker <universe@uap-core.de>
parents: 40
diff changeset
329 filelist = filelist->next;
c2e73e175341 replaced direct scanning of directories with a two-step approach (first: create filename list, second: scan)
Mike Becker <universe@uap-core.de>
parents: 40
diff changeset
330 free(freethis);
3
510d6b198dde Moved some functions to functions.c
Mike Becker <universe@uap-core.de>
parents: 1
diff changeset
331 }
510d6b198dde Moved some functions to functions.c
Mike Becker <universe@uap-core.de>
parents: 1
diff changeset
332 }

mercurial