Add string-specific memory pool

Intern strings so they can be compared by address and stored without
wasting space.

This library uses the macros in the obj_pool.h and trp.h to create a
memory pool for strings and expose an API for handling them.

[rr: added API docs]
[jn: with some API simplifications, new documentation and tests]

Signed-off-by: David Barr <david.barr@cordelta.com>
Signed-off-by: Ramkumar Ramachandra <artagnon@gmail.com>
Signed-off-by: Jonathan Nieder <jrnieder@gmail.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

vcs-svn/string_pool.c

@@ -0,0 +1,102 @@
+/*
+ * Licensed under a two-clause BSD-style license.
+ * See LICENSE for details.
+ */
+
+#include "git-compat-util.h"
+#include "trp.h"
+#include "obj_pool.h"
+#include "string_pool.h"
+
+static struct trp_root tree = { ~0 };
+
+struct node {
+	uint32_t offset;
+	struct trp_node children;
+};
+
+/* Two memory pools: one for struct node, and another for strings */
+obj_pool_gen(node, struct node, 4096)
+obj_pool_gen(string, char, 4096)
+
+static char *node_value(struct node *node)
+{
+	return node ? string_pointer(node->offset) : NULL;
+}
+
+static int node_cmp(struct node *a, struct node *b)
+{
+	return strcmp(node_value(a), node_value(b));
+}
+
+/* Build a Treap from the node structure (a trp_node w/ offset) */
+trp_gen(static, tree_, struct node, children, node, node_cmp);
+
+const char *pool_fetch(uint32_t entry)
+{
+	return node_value(node_pointer(entry));
+}
+
+uint32_t pool_intern(const char *key)
+{
+	/* Canonicalize key */
+	struct node *match = NULL, *node;
+	uint32_t key_len;
+	if (key == NULL)
+		return ~0;
+	key_len = strlen(key) + 1;
+	node = node_pointer(node_alloc(1));
+	node->offset = string_alloc(key_len);
+	strcpy(node_value(node), key);
+	match = tree_search(&tree, node);
+	if (!match) {
+		tree_insert(&tree, node);
+	} else {
+		node_free(1);
+		string_free(key_len);
+		node = match;
+	}
+	return node_offset(node);
+}
+
+uint32_t pool_tok_r(char *str, const char *delim, char **saveptr)
+{
+	char *token = strtok_r(str, delim, saveptr);
+	return token ? pool_intern(token) : ~0;
+}
+
+void pool_print_seq(uint32_t len, uint32_t *seq, char delim, FILE *stream)
+{
+	uint32_t i;
+	for (i = 0; i < len && ~seq[i]; i++) {
+		fputs(pool_fetch(seq[i]), stream);
+		if (i < len - 1 && ~seq[i + 1])
+			fputc(delim, stream);
+	}
+}
+
+uint32_t pool_tok_seq(uint32_t sz, uint32_t *seq, const char *delim, char *str)
+{
+	char *context = NULL;
+	uint32_t token = ~0;
+	uint32_t length;
+
+	if (sz == 0)
+		return ~0;
+	if (str)
+		token = pool_tok_r(str, delim, &context);
+	for (length = 0; length < sz; length++) {
+		seq[length] = token;
+		if (token == ~0)
+			return length;
+		token = pool_tok_r(NULL, delim, &context);
+	}
+	seq[sz - 1] = ~0;
+	return sz;
+}
+
+void pool_reset(void)
+{
+	node_reset();
+	string_reset();
+}

vcs-svn/string_pool.h

@@ -0,0 +1,11 @@
+#ifndef STRING_POOL_H_
+#define STRING_POOL_H_
+
+uint32_t pool_intern(const char *key);
+const char *pool_fetch(uint32_t entry);
+uint32_t pool_tok_r(char *str, const char *delim, char **saveptr);
+void pool_print_seq(uint32_t len, uint32_t *seq, char delim, FILE *stream);
+uint32_t pool_tok_seq(uint32_t sz, uint32_t *seq, const char *delim, char *str);
+void pool_reset(void);
+
+#endif

vcs-svn/string_pool.txt

@@ -0,0 +1,43 @@
+string_pool API
+===============
+
+The string_pool API provides facilities for replacing strings
+with integer keys that can be more easily compared and stored.
+The facilities are designed so that one could teach Git without
+too much trouble to store the information needed for these keys to
+remain valid over multiple executions.
+
+Functions
+---------
+
+pool_intern::
+	Include a string in the string pool and get its key.
+	If that string is already in the pool, retrieves its
+	existing key.
+
+pool_fetch::
+	Retrieve the string associated to a given key.
+
+pool_tok_r::
+	Extract the key of the next token from a string.
+	Interface mimics strtok_r.
+
+pool_print_seq::
+	Print a sequence of strings named by key to a file, using the
+	specified delimiter to separate them.
+
+	If NULL (key ~0) appears in the sequence, the sequence ends
+	early.
+
+pool_tok_seq::
+	Split a string into tokens, storing the keys of segments
+	into a caller-provided array.
+
+	Unless sz is 0, the array will always be ~0-terminated.
+	If there is not enough room for all the tokens, the
+	array holds as many tokens as fit in the entries before
+	the terminating ~0.  Return value is the index after the
+	last token, or sz if the tokens did not fit.
+
+pool_reset::
+	Deallocate storage for the string pool.