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         size_t nr;
  90         size_t alloc;
  91         unsigned int strdup_strings:1;
  92         compare_strings_fn cmp; /* NULL uses strcmp() */
  93 };
  94
  95 #define STRING_LIST_INIT_NODUP { 0 }
  96 #define STRING_LIST_INIT_DUP   { .strdup_strings = 1 }
  97
  98 /* General functions which work with both sorted and unsorted lists. */
  99
 100 /**
 101  * Initialize the members of a string_list pointer in the same way as
 102  * the corresponding `STRING_LIST_INIT_NODUP` and
 103  * `STRING_LIST_INIT_DUP` macros.
 104  */
 105 void string_list_init_nodup(struct string_list *list);
 106 void string_list_init_dup(struct string_list *list);
 107
 108 /** Callback function type for for_each_string_list */
 109 typedef int (*string_list_each_func_t)(struct string_list_item *, void *);
 110
 111 /**
 112  * Apply `want` to each item in `list`, retaining only the ones for which
 113  * the function returns true.  If `free_util` is true, call free() on
 114  * the util members of any items that have to be deleted.  Preserve
 115  * the order of the items that are retained.
 116  */
 117 void filter_string_list(struct string_list *list, int free_util,
 118                         string_list_each_func_t want, void *cb_data);
 119
 120 /**
 121  * Free a string_list. The `string` pointer of the items will be freed
 122  * in case the `strdup_strings` member of the string_list is set. The
 123  * second parameter controls if the `util` pointer of the items should
 124  * be freed or not.
 125  */
 126 void string_list_clear(struct string_list *list, int free_util);
 127
 128 /**
 129  * Callback type for `string_list_clear_func`.  The string associated
 130  * with the util pointer is passed as the second argument
 131  */
 132 typedef void (*string_list_clear_func_t)(void *p, const char *str);
 133
 134 /** Call a custom clear function on each util pointer */
 135 void string_list_clear_func(struct string_list *list, string_list_clear_func_t clearfunc);
 136
 137 /**
 138  * Apply `func` to each item. If `func` returns nonzero, the
 139  * iteration aborts and the return value is propagated.
 140  */
 141 int for_each_string_list(struct string_list *list,
 142                          string_list_each_func_t func, void *cb_data);
 143
 144 /** Iterate over each item, as a macro. */
 145 #define for_each_string_list_item(item,list)            \
 146         for (item = (list)->items;                      \
 147              item && item < (list)->items + (list)->nr; \
 148              ++item)
 149
 150 /**
 151  * Remove any empty strings from the list.  If free_util is true, call
 152  * free() on the util members of any items that have to be deleted.
 153  * Preserve the order of the items that are retained.
 154  */
 155 void string_list_remove_empty_items(struct string_list *list, int free_util);
 156
 157 /* Use these functions only on sorted lists: */
 158
 159 /** Determine if the string_list has a given string or not. */
 160 int string_list_has_string(const struct string_list *list, const char *string);
 161 int string_list_find_insert_index(const struct string_list *list, const char *string,
 162                                   int negative_existing_index);
 163
 164 /**
 165  * Insert a new element to the string_list. The returned pointer can
 166  * be handy if you want to write something to the `util` pointer of
 167  * the string_list_item containing the just added string. If the given
 168  * string already exists the insertion will be skipped and the pointer
 169  * to the existing item returned.
 170  *
 171  * Since this function uses xrealloc() (which die()s if it fails) if the
 172  * list needs to grow, it is safe not to check the pointer. I.e. you may
 173  * write `string_list_insert(...)->util = ...;`.
 174  */
 175 struct string_list_item *string_list_insert(struct string_list *list, const char *string);
 176
 177 /**
 178  * Remove the given string from the sorted list.  If the string
 179  * doesn't exist, the list is not altered.
 180  */
 181 void string_list_remove(struct string_list *list, const char *string,
 182                         int free_util);
 183
 184 /**
 185  * Check if the given string is part of a sorted list. If it is part of the list,
 186  * return the corresponding string_list_item, NULL otherwise.
 187  */
 188 struct string_list_item *string_list_lookup(struct string_list *list, const char *string);
 189
 190 /*
 191  * Remove all but the first of consecutive entries with the same
 192  * string value.  If free_util is true, call free() on the util
 193  * members of any items that have to be deleted.
 194  */
 195 void string_list_remove_duplicates(struct string_list *sorted_list, int free_util);
 196
 197
 198 /* Use these functions only on unsorted lists: */
 199
 200 /**
 201  * Add string to the end of list.  If list->strdup_string is set, then
 202  * string is copied; otherwise the new string_list_entry refers to the
 203  * input string.
 204  */
 205 struct string_list_item *string_list_append(struct string_list *list, const char *string);
 206
 207 /**
 208  * Like string_list_append(), except string is never copied.  When
 209  * list->strdup_strings is set, this function can be used to hand
 210  * ownership of a malloc()ed string to list without making an extra
 211  * copy.
 212  */
 213 struct string_list_item *string_list_append_nodup(struct string_list *list, char *string);
 214
 215 /**
 216  * Sort the list's entries by string value in order specified by list->cmp
 217  * (strcmp() if list->cmp is NULL).
 218  */
 219 void string_list_sort(struct string_list *list);
 220
 221 /**
 222  * Like `string_list_has_string()` but for unsorted lists. Linear in
 223  * size of the list.
 224  */
 225 int unsorted_string_list_has_string(struct string_list *list, const char *string);
 226
 227 /**
 228  * Like `string_list_lookup()` but for unsorted lists. Linear in size
 229  * of the list.
 230  */
 231 struct string_list_item *unsorted_string_list_lookup(struct string_list *list,
 232                                                      const char *string);
 233 /**
 234  * Remove an item from a string_list. The `string` pointer of the
 235  * items will be freed in case the `strdup_strings` member of the
 236  * string_list is set. The third parameter controls if the `util`
 237  * pointer of the items should be freed or not.
 238  */
 239 void unsorted_string_list_delete_item(struct string_list *list, int i, int free_util);
 240
 241 /**
 242  * Split string into substrings on character `delim` and append the
 243  * substrings to `list`.  The input string is not modified.
 244  * list->strdup_strings must be set, as new memory needs to be
 245  * allocated to hold the substrings.  If maxsplit is non-negative,
 246  * then split at most maxsplit times.  Return the number of substrings
 247  * appended to list.
 248  *
 249  * Examples:
 250  *   string_list_split(l, "foo:bar:baz", ':', -1) -> ["foo", "bar", "baz"]
 251  *   string_list_split(l, "foo:bar:baz", ':', 0) -> ["foo:bar:baz"]
 252  *   string_list_split(l, "foo:bar:baz", ':', 1) -> ["foo", "bar:baz"]
 253  *   string_list_split(l, "foo:bar:", ':', -1) -> ["foo", "bar", ""]
 254  *   string_list_split(l, "", ':', -1) -> [""]
 255  *   string_list_split(l, ":", ':', -1) -> ["", ""]
 256  */
 257 int string_list_split(struct string_list *list, const char *string,
 258                       int delim, int maxsplit);
 259
 260 /*
 261  * Like string_list_split(), except that string is split in-place: the
 262  * delimiter characters in string are overwritten with NULs, and the
 263  * new string_list_items point into string (which therefore must not
 264  * be modified or freed while the string_list is in use).
 265  * list->strdup_strings must *not* be set.
 266  */
 267 int string_list_split_in_place(struct string_list *list, char *string,
 268                                int delim, int maxsplit);
 269 #endif /* STRING_LIST_H */