string-list.h

   1 #ifndef STRING_LIST_H
   2 #define STRING_LIST_H
   3
   4 /**
   5  * The string_list API offers a data structure and functions to handle
   6  * sorted and unsorted arrays of strings.  A "sorted" list is one whose
   7  * entries are sorted by string value in the order specified by the `cmp`
   8  * member (`strcmp()` by default).
   9  *
  10  * The caller:
  11  *
  12  * . Allocates and clears a `struct string_list` variable.
  13  *
  14  * . Initializes the members. You might want to set the flag `strdup_strings`
  15  *   if the strings should be strdup()ed. For example, this is necessary
  16  *   when you add something like git_path("..."), since that function returns
  17  *   a static buffer that will change with the next call to git_path().
  18  *
  19  * If you need something advanced, you can manually malloc() the `items`
  20  * member (you need this if you add things later) and you should set the
  21  * `nr` and `alloc` members in that case, too.
  22  *
  23  * . Adds new items to the list, using `string_list_append`,
  24  *   `string_list_append_nodup`, `string_list_insert`,
  25  *   `string_list_split`, and/or `string_list_split_in_place`.
  26  *
  27  * . Can check if a string is in the list using `string_list_has_string` or
  28  *   `unsorted_string_list_has_string` and get it from the list using
  29  *   `string_list_lookup` for sorted lists.
  30  *
  31  * . Can sort an unsorted list using `string_list_sort`.
  32  *
  33  * . Can remove duplicate items from a sorted list using
  34  *   `string_list_remove_duplicates`.
  35  *
  36  * . Can remove individual items of an unsorted list using
  37  *   `unsorted_string_list_delete_item`.
  38  *
  39  * . Can remove items not matching a criterion from a sorted or unsorted
  40  *   list using `filter_string_list`, or remove empty strings using
  41  *   `string_list_remove_empty_items`.
  42  *
  43  * . Finally it should free the list using `string_list_clear`.
  44  *
  45  * Example:
  46  *
  47  *     struct string_list list = STRING_LIST_INIT_NODUP;
  48  *     int i;
  49  *
  50  *     string_list_append(&list, "foo");
  51  *     string_list_append(&list, "bar");
  52  *     for (i = 0; i < list.nr; i++)
  53  *             printf("%s\n", list.items[i].string)
  54  *
  55  * NOTE: It is more efficient to build an unsorted list and sort it
  56  * afterwards, instead of building a sorted list (`O(n log n)` instead of
  57  * `O(n^2)`).
  58  *
  59  * However, if you use the list to check if a certain string was added
  60  * already, you should not do that (using unsorted_string_list_has_string()),
  61  * because the complexity would be quadratic again (but with a worse factor).
  62  */
  63
  64 /**
  65  * Represents an item of the list. The `string` member is a pointer to the
  66  * string, and you may use the `util` member for any purpose, if you want.
  67  */
  68 struct string_list_item {
  69         char *string;
  70         void *util;
  71 };
  72
  73 typedef int (*compare_strings_fn)(const char *, const char *);
  74
  75 /**
  76  * Represents the list itself.
  77  *
  78  * . The array of items are available via the `items` member.
  79  * . The `nr` member contains the number of items stored in the list.
  80  * . The `alloc` member is used to avoid reallocating at every insertion.
  81  *   You should not tamper with it.
  82  * . Setting the `strdup_strings` member to 1 will strdup() the strings
  83  *   before adding them, see above.
  84  * . The `compare_strings_fn` member is used to specify a custom compare
  85  *   function, otherwise `strcmp()` is used as the default function.
  86  */
  87 struct string_list {
  88         struct string_list_item *items;
  89         unsigned int nr, alloc;
  90         unsigned int strdup_strings:1;
  91         compare_strings_fn cmp; /* NULL uses strcmp() */
  92 };
  93
  94 #define STRING_LIST_INIT_NODUP { NULL, 0, 0, 0, NULL }
  95 #define STRING_LIST_INIT_DUP   { NULL, 0, 0, 1, NULL }
  96
  97 /* General functions which work with both sorted and unsorted lists. */
  98
  99 /**
 100  * Initialize the members of the string_list, set `strdup_strings`
 101  * member according to the value of the second parameter.
 102  */
 103 void string_list_init(struct string_list *list, int strdup_strings);
 104
 105 /** Callback function type for for_each_string_list */
 106 typedef int (*string_list_each_func_t)(struct string_list_item *, void *);
 107
 108 /**
 109  * Apply `want` to each item in `list`, retaining only the ones for which
 110  * the function returns true.  If `free_util` is true, call free() on
 111  * the util members of any items that have to be deleted.  Preserve
 112  * the order of the items that are retained.
 113  */
 114 void filter_string_list(struct string_list *list, int free_util,
 115                         string_list_each_func_t want, void *cb_data);
 116
 117 /**
 118  * Free a string_list. The `string` pointer of the items will be freed
 119  * in case the `strdup_strings` member of the string_list is set. The
 120  * second parameter controls if the `util` pointer of the items should
 121  * be freed or not.
 122  */
 123 void string_list_clear(struct string_list *list, int free_util);
 124
 125 /**
 126  * Callback type for `string_list_clear_func`.  The string associated
 127  * with the util pointer is passed as the second argument
 128  */
 129 typedef void (*string_list_clear_func_t)(void *p, const char *str);
 130
 131 /** Call a custom clear function on each util pointer */
 132 void string_list_clear_func(struct string_list *list, string_list_clear_func_t clearfunc);
 133
 134 /**
 135  * Apply `func` to each item. If `func` returns nonzero, the
 136  * iteration aborts and the return value is propagated.
 137  */
 138 int for_each_string_list(struct string_list *list,
 139                          string_list_each_func_t func, void *cb_data);
 140
 141 /** Iterate over each item, as a macro. */
 142 #define for_each_string_list_item(item,list)            \
 143         for (item = (list)->items;                      \
 144              item && item < (list)->items + (list)->nr; \
 145              ++item)
 146
 147 /**
 148  * Remove any empty strings from the list.  If free_util is true, call
 149  * free() on the util members of any items that have to be deleted.
 150  * Preserve the order of the items that are retained.
 151  */
 152 void string_list_remove_empty_items(struct string_list *list, int free_util);
 153
 154 /* Use these functions only on sorted lists: */
 155
 156 /** Determine if the string_list has a given string or not. */
 157 int string_list_has_string(const struct string_list *list, const char *string);
 158 int string_list_find_insert_index(const struct string_list *list, const char *string,
 159                                   int negative_existing_index);
 160
 161 /**
 162  * Insert a new element to the string_list. The returned pointer can
 163  * be handy if you want to write something to the `util` pointer of
 164  * the string_list_item containing the just added string. If the given
 165  * string already exists the insertion will be skipped and the pointer
 166  * to the existing item returned.
 167  *
 168  * Since this function uses xrealloc() (which die()s if it fails) if the
 169  * list needs to grow, it is safe not to check the pointer. I.e. you may
 170  * write `string_list_insert(...)->util = ...;`.
 171  */
 172 struct string_list_item *string_list_insert(struct string_list *list, const char *string);
 173
 174 /**
 175  * Remove the given string from the sorted list.  If the string
 176  * doesn't exist, the list is not altered.
 177  */
 178 void string_list_remove(struct string_list *list, const char *string,
 179                         int free_util);
 180
 181 /**
 182  * Check if the given string is part of a sorted list. If it is part of the list,
 183  * return the corresponding string_list_item, NULL otherwise.
 184  */
 185 struct string_list_item *string_list_lookup(struct string_list *list, const char *string);
 186
 187 /*
 188  * Remove all but the first of consecutive entries with the same
 189  * string value.  If free_util is true, call free() on the util
 190  * members of any items that have to be deleted.
 191  */
 192 void string_list_remove_duplicates(struct string_list *sorted_list, int free_util);
 193
 194
 195 /* Use these functions only on unsorted lists: */
 196
 197 /**
 198  * Add string to the end of list.  If list->strdup_string is set, then
 199  * string is copied; otherwise the new string_list_entry refers to the
 200  * input string.
 201  */
 202 struct string_list_item *string_list_append(struct string_list *list, const char *string);
 203
 204 /**
 205  * Like string_list_append(), except string is never copied.  When
 206  * list->strdup_strings is set, this function can be used to hand
 207  * ownership of a malloc()ed string to list without making an extra
 208  * copy.
 209  */
 210 struct string_list_item *string_list_append_nodup(struct string_list *list, char *string);
 211
 212 /**
 213  * Sort the list's entries by string value in order specified by list->cmp
 214  * (strcmp() if list->cmp is NULL).
 215  */
 216 void string_list_sort(struct string_list *list);
 217
 218 /**
 219  * Like `string_list_has_string()` but for unsorted lists. Linear in
 220  * size of the list.
 221  */
 222 int unsorted_string_list_has_string(struct string_list *list, const char *string);
 223
 224 /**
 225  * Like `string_list_lookup()` but for unsorted lists. Linear in size
 226  * of the list.
 227  */
 228 struct string_list_item *unsorted_string_list_lookup(struct string_list *list,
 229                                                      const char *string);
 230 /**
 231  * Remove an item from a string_list. The `string` pointer of the
 232  * items will be freed in case the `strdup_strings` member of the
 233  * string_list is set. The third parameter controls if the `util`
 234  * pointer of the items should be freed or not.
 235  */
 236 void unsorted_string_list_delete_item(struct string_list *list, int i, int free_util);
 237
 238 /**
 239  * Split string into substrings on character `delim` and append the
 240  * substrings to `list`.  The input string is not modified.
 241  * list->strdup_strings must be set, as new memory needs to be
 242  * allocated to hold the substrings.  If maxsplit is non-negative,
 243  * then split at most maxsplit times.  Return the number of substrings
 244  * appended to list.
 245  *
 246  * Examples:
 247  *   string_list_split(l, "foo:bar:baz", ':', -1) -> ["foo", "bar", "baz"]
 248  *   string_list_split(l, "foo:bar:baz", ':', 0) -> ["foo:bar:baz"]
 249  *   string_list_split(l, "foo:bar:baz", ':', 1) -> ["foo", "bar:baz"]
 250  *   string_list_split(l, "foo:bar:", ':', -1) -> ["foo", "bar", ""]
 251  *   string_list_split(l, "", ':', -1) -> [""]
 252  *   string_list_split(l, ":", ':', -1) -> ["", ""]
 253  */
 254 int string_list_split(struct string_list *list, const char *string,
 255                       int delim, int maxsplit);
 256
 257 /*
 258  * Like string_list_split(), except that string is split in-place: the
 259  * delimiter characters in string are overwritten with NULs, and the
 260  * new string_list_items point into string (which therefore must not
 261  * be modified or freed while the string_list is in use).
 262  * list->strdup_strings must *not* be set.
 263  */
 264 int string_list_split_in_place(struct string_list *list, char *string,
 265                                int delim, int maxsplit);
 266 #endif /* STRING_LIST_H */