Data Structures and Algorithms!

Jennifer Rexford!

The material for this lecture is drawn, in part, from!

The Practice of Programming (Kernighan & Pike) Chapter 2!

1
Motivating Quotations!
Every program depends on algorithms and data
structures, but few programs depend on the
invention of brand new ones.!
-- Kernighan & Pike!

I will, in fact, claim that the difference between a

bad programmer and a good one is whether he
considers his code or his data structures more
important. Bad programmers worry about the
code. Good programmers worry about data
structures and their relationships.!
-- Linus Torvalds!
2
Goals of this Lecture!
Help you learn (or refresh your memory) about:!
Common data structures and algorithms!

Why? Shallow motivation:!

Provide examples of pointer-related C code!

Why? Deeper motivation:!

Common data structures and algorithms serve as high
level building blocks!
A power programmer:!
Rarely creates programs from scratch!
Often creates programs using building blocks!

3
A Common Task!
Maintain a table of key/value pairs!
Each key is a string; each value is an int
Unknown number of key-value pairs!

Examples!
(student name, grade)!
(john smith, 84), (jane doe, 93), (bill clinton, 81)!
(baseball player, number)!
(Ruth, 3), (Gehrig, 4), (Mantle, 7)!
(variable name, value)!
(maxLength, 2000), (i, 7), (j, -10)!

For simplicity, allow duplicate keys (client responsibility)!

In Assignment #3, must check for duplicate keys!! 4
Data Structures and Algorithms!
Data structures!
Linked list of key/value pairs!
Hash table of key/value pairs!

Algorithms!
Create: Create the data structure!
Add: Add a key/value pair!
Search: Search for a key/value pair, by key!
Free: Free the data structure!

5
Data Structure #1: Linked List!
Data structure: Nodes; each contains key/value
pair and pointer to next node!

"Mantle" "Gehrig" "Ruth"

7 4 3
NULL

Algorithms:!
Create: Allocate Table structure to point to first node!
Add: Insert new node at front of list!
Search: Linear search through the list!
Free: Free nodes while traversing; free Table structure!
6
Linked List: Data Structure!
struct Node {
const char *key;
int value;
struct Node *next;
};

struct Table {
struct Node *first;
};

struct! struct!
struct! Node! Node!
Table!
"Gehrig" "Ruth"
4 3
NULL

7
Linked List: Create (1)!
struct Table *Table_create(void) {
struct Table *t;
t = (struct Table*)
malloc(sizeof(struct Table));
t->first = NULL;
return t;
}

struct Table *t;

t = Table_create();

t!

8
Linked List: Create (2)!
struct Table *Table_create(void) {
struct Table *t;
t = (struct Table*)
malloc(sizeof(struct Table));
t->first = NULL;
return t;
}

struct Table *t;

t = Table_create();

t!

NULL

9
Linked List: Add (1)!
void Table_add(struct Table *t,
const char *key, int value) {
struct Node *p = (struct Node*)malloc(sizeof(struct Node));
p->key = key;
p->value = value;
p->next = t->first;
t->first = p;
}

struct Table *t;

These are Table_add(t, "Ruth", 3);
pointers to! Table_add(t, "Gehrig", 4);
strings! Table_add(t, "Mantle", 7);

t!
"Gehrig" "Ruth"
4 3
NULL

10
Linked List: Add (2)!
void Table_add(struct Table *t,
const char *key, int value) {
struct Node *p = (struct Node*)malloc(sizeof(struct Node));
p->key = key;
p->value = value;
p->next = t->first;
t->first = p;
}

struct Table *t;

p! Table_add(t, "Ruth", 3);
Table_add(t, "Gehrig", 4);
Table_add(t, "Mantle", 7);

t!
"Gehrig" "Ruth"
4 3
NULL

11
Linked List: Add (3)!
void Table_add(struct Table *t,
const char *key, int value) {
struct Node *p = (struct Node*)malloc(sizeof(struct Node));
p->key = key;
p->value = value;
p->next = t->first;
t->first = p;
}

struct Table *t;

p! Table_add(t, "Ruth", 3);
Table_add(t, "Gehrig", 4);
Table_add(t, "Mantle", 7);
"Mantle"
t! 7

"Gehrig" "Ruth"
4 3
NULL

12
Linked List: Add (4)!
void Table_add(struct Table *t,
const char *key, int value) {
struct Node *p = (struct Node*)malloc(sizeof(struct Node));
p->key = key;
p->value = value;
p->next = t->first;
t->first = p;
}

struct Table *t;

p! Table_add(t, "Ruth", 3);
Table_add(t, "Gehrig", 4);
Table_add(t, "Mantle", 7);
"Mantle"
t! 7

"Gehrig" "Ruth"
4 3
NULL

13
Linked List: Add (5)!
void Table_add(struct Table *t,
const char *key, int value) {
struct Node *p = (struct Node*)malloc(sizeof(struct Node));
p->key = key;
p->value = value;
p->next = t->first;
t->first = p;
}

struct Table *t;

p! Table_add(t, "Ruth", 3);
Table_add(t, "Gehrig", 4);
Table_add(t, "Mantle", 7);
"Mantle"
t! 7

"Gehrig" "Ruth"
4 3
NULL

14
Linked List: Search (1)!
int Table_search(struct Table *t,
const char *key, int *value) {
struct Node *p;
for (p = t->first; p != NULL; p = p->next)
if (strcmp(p->key, key) == 0) {
*value = p->value;
return 1;
} struct Table *t;
return 0; int value;
} int found;

found =
Table_search(t, "Gehrig", &value);

t!

"Mantle" "Gehrig" "Ruth"

7 4 3
NULL

15
Linked List: Search (2)!
int Table_search(struct Table *t,
const char *key, int *value) {
struct Node *p;
for (p = t->first; p != NULL; p = p->next)
if (strcmp(p->key, key) == 0) {
*value = p->value;
return 1;
} struct Table *t;
return 0; int value;
} int found;

found =
Table_search(t, "Gehrig", &value);

p!
t!

"Mantle" "Gehrig" "Ruth"

7 4 3
NULL

16
Linked List: Search (3)!
int Table_search(struct Table *t,
const char *key, int *value) {
struct Node *p;
for (p = t->first; p != NULL; p = p->next)
if (strcmp(p->key, key) == 0) {
*value = p->value;
return 1;
} struct Table *t;
return 0; int value;
} int found;

found =
Table_search(t, "Gehrig", &value);

p!
t!

"Mantle" "Gehrig" "Ruth"

7 4 3
NULL

17
Linked List: Search (4)!
int Table_search(struct Table *t,
const char *key, int *value) {
struct Node *p;
for (p = t->first; p != NULL; p = p->next)
if (strcmp(p->key, key) == 0) {
*value = p->value;
return 1;
} struct Table *t;
return 0; int value;
} int found;

found =
Table_search(t, "Gehrig", &value);

p!
t!

"Mantle" "Gehrig" "Ruth"

7 4 3
NULL

18
Linked List: Search (5)!
int Table_search(struct Table *t,
const char *key, int *value) {
struct Node *p;
for (p = t->first; p != NULL; p = p->next)
if (strcmp(p->key, key) == 0) {
*value = p->value;
return 1;
} struct Table *t;
return 0; int value;
} int found;

found =
Table_search(t, "Gehrig", &value);

p!
t!

"Mantle" "Gehrig" "Ruth"

7 4 3
NULL

19
Linked List: Search (6)!
int Table_search(struct Table *t,
const char *key, int *value) {
struct Node *p;
for (p = t->first; p != NULL; p = p->next)
if (strcmp(p->key, key) == 0) {
*value = p->value;
return 1;
} struct Table *t;
return 0; int value;
} int found;

found =
Table_search(t, "Gehrig", &value);

1
p! 4
t!

"Mantle" "Gehrig" "Ruth"

7 4 3
NULL

20
Linked List: Free (1)!
void Table_free(struct Table *t) {
struct Node *p;
struct Node *nextp;
for (p = t->first; p != NULL; p = nextp) {
nextp = p->next;
free(p);
}
free(t);
}

struct Table *t;

Table_free(t);

t!
"Mantle" "Gehrig" "Ruth"
7 4 3
NULL

21
Linked List: Free (2)!
void Table_free(struct Table *t) {
struct Node *p;
struct Node *nextp;
for (p = t->first; p != NULL; p = nextp) {
nextp = p->next;
free(p);
}
free(t);
}

struct Table *t;

Table_free(t);

p!
t!
"Mantle" "Gehrig" "Ruth"
7 4 3
NULL

22
Linked List: Free (3)!
void Table_free(struct Table *t) {
struct Node *p;
struct Node *nextp;
for (p = t->first; p != NULL; p = nextp) {
nextp = p->next;
free(p);
}
free(t);
}

struct Table *t;

Table_free(t);

p! nextp!
t!
"Mantle" "Gehrig" "Ruth"
7 4 3
NULL

23
Linked List: Free (4)!
void Table_free(struct Table *t) {
struct Node *p;
struct Node *nextp;
for (p = t->first; p != NULL; p = nextp) {
nextp = p->next;
free(p);
}
free(t);
}

struct Table *t;

Table_free(t);

p! nextp!
t!
"Mantle" "Gehrig" "Ruth"
7 4 3
NULL

24
Linked List: Free (5)!
void Table_free(struct Table *t) {
struct Node *p;
struct Node *nextp;
for (p = t->first; p != NULL; p = nextp) {
nextp = p->next;
free(p);
}
free(t);
}

struct Table *t;

Table_free(t);

p! nextp!
t!
"Mantle" "Gehrig" "Ruth"
7 4 3
NULL

25
Linked List: Free (6)!
void Table_free(struct Table *t) {
struct Node *p;
struct Node *nextp;
for (p = t->first; p != NULL; p = nextp) {
nextp = p->next;
free(p);
}
free(t);
}

struct Table *t;

Table_free(t);

p! nextp!
t!
"Mantle" "Gehrig" "Ruth"
7 4 3
NULL

26
Linked List: Free (7)!
void Table_free(struct Table *t) {
struct Node *p;
struct Node *nextp;
for (p = t->first; p != NULL; p = nextp) {
nextp = p->next;
free(p);
}
free(t);
}

struct Table *t;

Table_free(t);

p! nextp!
t!
"Mantle" "Gehrig" "Ruth"
7 4 3
NULL

27
Linked List: Free (8)!
void Table_free(struct Table *t) {
struct Node *p;
struct Node *nextp;
for (p = t->first; p != NULL; p = nextp) {
nextp = p->next;
free(p);
}
free(t);
}

struct Table *t;

Table_free(t);

p! nextp!
t!
"Mantle" "Gehrig" "Ruth"
7 4 3
NULL

28
Linked List: Free (9)!
void Table_free(struct Table *t) {
struct Node *p;
struct Node *nextp;
for (p = t->first; p != NULL; p = nextp) {
nextp = p->next;
free(p);
}
free(t)
}

struct Table *t;

Table_free(t);

p! nextp!
t!
"Mantle" "Gehrig" "Ruth"
7 4 3
NULL

29
Linked List Performance!

Create: !fast!
What are the
Add:! !fast! asymptotic run times
Search: !slow! (big-oh notation)?!

Free: !slow!

Would it be better to
keep the nodes
sorted by key?!

30
Data Structure #2: Hash Table!
Fixed-size array where each element points to a linked list!
0

ARRAYSIZE-1

struct Node *array[ARRAYSIZE];

Function maps each key to an array index !

For example, for an integer key h
Hash function: i = h % ARRAYSIZE (mod function)!
Go to array element i, i.e., the linked list hashtab[i]
Search for element, add element, remove element, etc.!
31
Hash Table Example!
Integer keys, array of size 5 with hash function h
mod 5 !
1776 % 5 is 1!
1861 % 5 is 1!
1939 % 5 is 4!

1776 1861
0
Revolution Civil
1
2
3
4
1939
WW2

32
How Large an Array?!
Large enough that average bucket size is 1!
Short buckets mean fast search!
Long buckets mean slow search!

Small enough to be memory efficient!

Not an excessive number of elements!
Fortunately, each array element is just storing a pointer!

This is OK:!
0

ARRAYSIZE-1
33
What Kind of Hash Function?!
Good at distributing elements across the array!
Distribute results over the range 0, 1, , ARRAYSIZE-1!
Distribute results evenly to avoid very long buckets!

This is not so good:!

ARRAYSIZE-1
What would be the
worst possible hash
function?!
34
Hashing String Keys to Integers!
Simple schemes dont distribute the keys evenly enough!
Number of characters, mod ARRAYSIZE!
Sum the ASCII values of all characters, mod ARRAYSIZE!
!

Heres a reasonably good hash function!

Weighted sum of characters xi in the string!
( aixi) mod ARRAYSIZE!
Best if a and ARRAYSIZE are relatively prime!
E.g., a = 65599, ARRAYSIZE = 1024!

35
Implementing Hash Function!
Potentially expensive to compute ai for each value of i!
Computing ai for each value of I!
Instead, do (((x[0] * 65599 + x[1]) * 65599 + x[2]) * 65599 + x[3]) * !

unsigned int hash(const char *x) {

int i;
unsigned int h = 0U;
for (i=0; x[i]!='\0'; i++)
h = h * 65599 + (unsigned char)x[i];
return h % 1024;
}

Can be more clever than this for powers of two!!

(Described in Appendix)!
36
Hash Table Example!
Example: ARRAYSIZE = 7!
Lookup (and enter, if not present) these strings: the, cat, in, the, hat!
Hash table initially empty.!
First word: the. hash(the) = 965156977. 965156977 % 7 = 1.!
Search the linked list table[1] for the string the; not found.!

0
1
2
3
4
5
6
37
Hash Table Example (cont.)!
Example: ARRAYSIZE = 7!
Lookup (and enter, if not present) these strings: the, cat, in, the, hat!
Hash table initially empty.!
First word: the. hash(the) = 965156977. 965156977 % 7 = 1.!
Search the linked list table[1] for the string the; not found!
Now: table[1] = makelink(key, value, table[1])!

0
the
1
2
3
4
5
6
38
Hash Table Example (cont.)!
Second word: cat. hash(cat) = 3895848756. 3895848756 % 7 = 2.!

Search the linked list table[2] for the string cat; not found!
Now: table[2] = makelink(key, value, table[2])!

0
the
1
2
3
4
5
6
39
Hash Table Example (cont.)!
Third word: in. hash(in) = 6888005. 6888005% 7 = 5.!
Search the linked list table[5] for the string in; not found!
Now: table[5] = makelink(key, value, table[5])!

0
the
1
2
3 cat
4
5
6
40
Hash Table Example (cont.)!
Fourth word: the. hash(the) = 965156977. 965156977 % 7 = 1.!
Search the linked list table[1] for the string the; found it!!

0
the
1
2
3 cat
4
in
5
6
41
Hash Table Example (cont.)!
Fourth word: hat. hash(hat) = 865559739. 865559739 % 7 = 2.!
Search the linked list table[2] for the string hat; not found.!
Now, insert hat into the linked list table[2]. !
At beginning or end? Doesnt matter.!

0
the
1
2
3 cat
4
in
5
6
42
Hash Table Example (cont.)!
Inserting at the front is easier, so add hat at the front !

0
the
1
2
3 hat cat
4
in
5
6
43
Hash Table: Data Structure!

enum {BUCKET_COUNT = 1024};

struct Node {
const char *key;
int value; struct!
struct Node *next;
struct!
Table!
}; Node!
0 NULL struct!
struct Table { "Ruth"
1 NULL

struct Node *array[BUCKET_COUNT]; 3 Node!
}; 23 NULL
"Gehrig"
723 4

NULL
806 NULL

1023 NULL

44
Hash Table: Create!
struct Table *Table_create(void) {
struct Table *t;
t = (struct Table*)calloc(1, sizeof(struct Table));
return t;
}

struct Table *t;

t = Table_create();

t!

0 NULL
1 NULL

1023 NULL

45
Hash Table: Add (1)!
void Table_add(struct Table *t,
const char *key, int value) {
struct Node *p = (struct Node*)malloc(sizeof(struct Node));
int h = hash(key);
p->key = key;
p->value = value; struct Table *t;
p->next = t->array[h];
t->array[h] = p; Table_add(t, "Ruth", 3);
} Table_add(t, "Gehrig", 4);
Table_add(t, "Mantle", 7);

t!
These are
pointers to
0 NULL "Ruth" strings!
1 NULL
3
NULL
23 "Gehrig"
4
723 NULL Pretend that Ruth!
806 NULL
hashed to 23 and!
1023 NULL Gehrig to 723!
46
Hash Table: Add (2)!
void Table_add(struct Table *t,
const char *key, int value) {
struct Node *p = (struct Node*)malloc(sizeof(struct Node));
int h = hash(key);
p->key = key;
p->value = value; struct Table *t;
p->next = t->array[h];
t->array[h] = p; Table_add(t, "Ruth", 3);
} Table_add(t, "Gehrig", 4);
Table_add(t, "Mantle", 7);

t!

0 NULL "Ruth"
1 NULL
3
NULL
23 "Gehrig" p!
4
723 NULL
806 NULL

1023 NULL
47
Hash Table: Add (3)!
void Table_add(struct Table *t,
const char *key, int value) {
struct Node *p = (struct Node*)malloc(sizeof(struct Node));
int h = hash(key);
p->key = key;
p->value = value; struct Table *t;
p->next = t->array[h];
t->array[h] = p; Table_add(t, "Ruth", 3);
} Table_add(t, "Gehrig", 4);
Table_add(t, "Mantle", 7);

t!
Pretend that Mantle!
hashed to 806, and so!
0 NULL "Ruth"
1 NULL 3
h = 806!

NULL
23 "Gehrig" p!
4
723 NULL
806 NULL

"Mantle"
7
1023 NULL
48
Hash Table: Add (4)!
void Table_add(struct Table *t,
const char *key, int value) {
struct Node *p = (struct Node*)malloc(sizeof(struct Node));
int h = hash(key);
p->key = key;
p->value = value; struct Table *t;
p->next = t->array[h];
t->array[h] = p; Table_add(t, "Ruth", 3);
} Table_add(t, "Gehrig", 4);
Table_add(t, "Mantle", 7);

t!

0 NULL "Ruth" h = 806!

1 NULL
3
NULL
23 "Gehrig" p!
4
723 NULL
806 NULL

"Mantle"
7
1023 NULL NULL
49
Hash Table: Add (5)!
void Table_add(struct Table *t,
const char *key, int value) {
struct Node *p = (struct Node*)malloc(sizeof(struct Node));
int h = hash(key);
p->key = key;
p->value = value; struct Table *t;
p->next = t->array[h];
t->array[h] = p; Table_add(t, "Ruth", 3);
} Table_add(t, "Gehrig", 4);
Table_add(t, "Mantle", 7);

t!

0 NULL "Ruth" h = 806!

1 NULL
3
NULL
23 "Gehrig" p!
4
723 NULL
806 "Mantle"

7
1023 NULL NULL
50
Hash Table: Search (1)!
int Table_search(struct Table *t,
const char *key, int *value) {
struct Node *p;
int h = hash(key);
for (p = t->array[h]; p != NULL; p = p->next)
if (strcmp(p->key, key) == 0) { struct Table *t;
*value = p->value; int value;
return 1; int found;
}
return 0; found =
} Table_search(t, "Gehrig", &value);

t!

0 NULL
1 NULL
"Ruth"
3
23 NULL "Gehrig"
723 4

NULL "Mantle"
806 7
1023 NULL NULL 51
Hash Table: Search (2)!
int Table_search(struct Table *t,
const char *key, int *value) {
struct Node *p;
int h = hash(key);
for (p = t->array[h]; p != NULL; p = p->next)
if (strcmp(p->key, key) == 0) { struct Table *t;
*value = p->value; int value;
return 1; int found;
}
return 0; found =
} Table_search(t, "Gehrig", &value);

t!
Pretend that Gehrig!
0 NULL hashed to 723, and so!
1 NULL
"Ruth"
3
h = 723!
23 NULL "Gehrig"
723 4

NULL "Mantle"
806 7
1023 NULL NULL 52
Hash Table: Search (3)!
int Table_search(struct Table *t,
const char *key, int *value) {
struct Node *p;
int h = hash(key);
for (p = t->array[h]; p != NULL; p = p->next)
if (strcmp(p->key, key) == 0) { struct Table *t;
*value = p->value; int value;
return 1; int found;
}
return 0; found =
} Table_search(t, "Gehrig", &value);

t!

0 NULL p! h = 723!
1 NULL
"Ruth"
3
23 NULL "Gehrig"
723 4

NULL "Mantle"
806 7
1023 NULL NULL 53
Hash Table: Search (4)!
int Table_search(struct Table *t,
const char *key, int *value) {
struct Node *p;
int h = hash(key);
for (p = t->array[h]; p != NULL; p = p->next)
if (strcmp(p->key, key) == 0) { struct Table *t;
*value = p->value; int value;
return 1; int found;
}
return 0; found =
} Table_search(t, "Gehrig", &value);

t!

0 NULL p! h = 723!
1 NULL
"Ruth"
3
23 NULL "Gehrig"
723 4

NULL "Mantle"
806 7
1023 NULL NULL 54
Hash Table: Search (5)!
int Table_search(struct Table *t,
const char *key, int *value) {
struct Node *p;
int h = hash(key);
for (p = t->array[h]; p != NULL; p = p->next)
if (strcmp(p->key, key) == 0) { struct Table *t;
*value = p->value; int value;
return 1; int found;
}
return 0; found =
} Table_search(t, "Gehrig", &value);

t!
1
0 NULL p! h = 723!
1 NULL 4
"Ruth"
3
23 NULL "Gehrig"
723 4

NULL "Mantle"
806 7
1023 NULL NULL 55
Hash Table: Free (1)!
void Table_free(struct Table *t) {
struct Node *p;
struct Node *nextp;
int b;
for (b = 0; b < BUCKET_COUNT; b++)
for (p = t->array[b]; p != NULL; p = nextp) {
nextp = p->next;
free(p); struct Table *t;
}
free(t); Table_free(t);
}

t!

0 NULL
1 NULL
"Ruth"
3
23 NULL "Gehrig"
723 4

NULL "Mantle"
806 7
1023 NULL NULL 56
Hash Table: Free (2)!
void Table_free(struct Table *t) {
struct Node *p;
struct Node *nextp;
int b;
for (b = 0; b < BUCKET_COUNT; b++)
for (p = t->array[b]; p != NULL; p = nextp) {
nextp = p->next;
free(p); struct Table *t;
}
free(t); Table_free(t);
}

t!
b = 0!
0 NULL
1 NULL
"Ruth"
3
23 NULL "Gehrig"
723 4

NULL "Mantle"
806 7
1023 NULL NULL 57
Hash Table: Free (3)!
void Table_free(struct Table *t) {
struct Node *p;
struct Node *nextp;
int b;
for (b = 0; b < BUCKET_COUNT; b++)
for (p = t->array[b]; p != NULL; p = nextp) {
nextp = p->next;
free(p); struct Table *t;
}
free(t); Table_free(t);
}

t!
p!
b = 0!
0 NULL
1 NULL
"Ruth"
3
23 NULL "Gehrig"
723 4

NULL "Mantle"
806 7
1023 NULL NULL 58
Hash Table: Free (4)!
void Table_free(struct Table *t) {
struct Node *p;
struct Node *nextp;
int b;
for (b = 0; b < BUCKET_COUNT; b++)
for (p = t->array[b]; p != NULL; p = nextp) {
nextp = p->next;
free(p); struct Table *t;
}
free(t); Table_free(t);
}

t!
p!
b = 1, , 23!
0 NULL
1 NULL
"Ruth"
3
23 NULL "Gehrig"
723 4

NULL "Mantle"
806 7
1023 NULL NULL 59
Hash Table: Free (5)!
void Table_free(struct Table *t) {
struct Node *p;
struct Node *nextp;
int b;
for (b = 0; b < BUCKET_COUNT; b++)
for (p = t->array[b]; p != NULL; p = nextp) {
nextp = p->next;
free(p); struct Table *t;
}
free(t); Table_free(t);
}

t! p!
b = 23!
0 NULL
1 NULL
"Ruth"
3
23 NULL "Gehrig"
723 4

NULL "Mantle"
806 7
1023 NULL NULL 60
Hash Table: Free (6)!
void Table_free(struct Table *t) {
struct Node *p;
struct Node *nextp;
int b;
for (b = 0; b < BUCKET_COUNT; b++)
for (p = t->array[b]; p != NULL; p = nextp) {
nextp = p->next;
free(p); struct Table *t;
}
free(t); Table_free(t);
}

t! p!
nextp!
b = 23!
0 NULL
1 NULL
"Ruth"
3
23 NULL "Gehrig"
723 4

NULL "Mantle"
806 7
1023 NULL NULL 61
Hash Table: Free (7)!
void Table_free(struct Table *t) {
struct Node *p;
struct Node *nextp;
int b;
for (b = 0; b < BUCKET_COUNT; b++)
for (p = t->array[b]; p != NULL; p = nextp) {
nextp = p->next;
free(p); struct Table *t;
}
free(t); Table_free(t);
}

t!
p! nextp!
b = 23!
0 NULL
1 NULL
"Ruth"
3
23 NULL "Gehrig"
723 4

NULL "Mantle"
806 7
1023 NULL NULL 62
Hash Table: Free (8)!
void Table_free(struct Table *t) {
struct Node *p;
struct Node *nextp;
int b;
for (b = 0; b < BUCKET_COUNT; b++)
for (p = t->array[b]; p != NULL; p = nextp) {
nextp = p->next;
free(p); struct Table *t;
}
free(t); Table_free(t);
}

t!
b = 24, , 723!
0 NULL
b = 724, , 806!
1 NULL
"Ruth"
b = 807, , 1024!
3
23 NULL "Gehrig"
723 4

NULL "Mantle"
806 7
1023 NULL NULL 63
Hash Table: Free (9)!
void Table_free(struct Table *t) {
struct Node *p;
struct Node *nextp;
int b;
for (b = 0; b < BUCKET_COUNT; b++)
for (p = t->array[b]; p != NULL; p = nextp) {
nextp = p->next;
free(p); struct Table *t;
}
free(t); Table_free(t);
}

t!
b = 1024!
0 NULL
1 NULL
"Ruth"
3
23 NULL "Gehrig"
723 4

NULL "Mantle"
806 7
1023 NULL NULL 64
Hash Table Performance!

Create: !fast!
What are the
Add: !fast! asymptotic run times
Search: !fast! (big-oh notation)?!

Free: !slow!

Is hash table
search always
fast?!

65
Key Ownership!

Note: Table_add() functions contain this code:!

void Table_add(struct Table *t, const char *key, int value) {

struct Node *p = (struct Node*)malloc(sizeof(struct Node));
p->key = key;

}

Caller passes key, which is a pointer to memory where a string

resides!
Table_add() function stores within the table the address where the
string resides!

66
Key Ownership (cont.)!
Problem: Consider this calling code:!
struct Table t; Via Table_add(), table contains
char k[100] = "Ruth";
memory address k!

Table_add(t, k, 3); Client changes string at
strcpy(k, "Gehrig"); memory address k!
Thus client changes key within table!

What happens if the What happens if the

client searches t for client searches t for
Ruth?! Gehrig?!

67
Key Ownership (cont.)!
Solution: Table_add() saves copy of given key!
void Table_add(struct Table *t, const char *key, int value) {

struct Node *p = (struct Node*)malloc(sizeof(struct Node));
p->key = (const char*)malloc(strlen(key) + 1);
strcpy(p->key, key);

} Why add 1?!

If client changes string at memory address k, data structure is not

affected!

Then the data structure owns the copy, that is:!

The data structure is responsible for freeing the memory in which
the copy resides!
The Table_free() function must free the copy!
68
Summary!
Common data structures & associated algorithms!
Linked list!
Fast insert, slow search!
Hash table!
Fast insert, (potentially) fast search!
Invaluable for storing key/value pairs!
Very common!

Related issues!
Hashing algorithms!
Memory ownership!

69
Appendix!

Stupid programmer tricks related to hash tables!

70
Revisiting Hash Functions!
Potentially expensive to compute mod c!
Involves division by c and keeping the remainder!
Easier when c is a power of 2 (e.g., 16 = 24)!
An alternative (by example)!
53 = 32 + 16 + 4 + 1!
32 16 8 4 2 1
0 0 1 1 0 1 0 1

53 % 16 is 5, the last four bits of the number!

32 16 8 4 2 1
0 0 0 0 0 1 0 1

Would like an easy way to isolate the last four bits ! 71

Recall: Bitwise Operators in C!
Bitwise AND (&)! Bitwise OR (|)!
& 0 1 | 0 1
0 0 0 0 0 1
1 0 1 1 1 1
Mod on the cheap!!
E.g., h = 53 & 15;!
Ones complement (~)!
53 0 0 1 1 0 1 0 1 Turns 0 to 1, and 1 to 0!
E.g., set last three bits to 0!
& 15 0 0 0 0 1 1 1 1 x = x & ~7;!

5 0 0 0 0 0 1 0 1
72
A Faster Hash Function!
unsigned int hash(const char *x) {
int i;
unsigned int h = 0U;
for (i=0; x[i]!='\0'; i++) Previous!
h = h * 65599 + (unsigned char)x[i]; version!
return h % 1024;
}

unsigned int hash(const char *x) {

int i;
unsigned int h = 0U;
for (i=0; x[i]!='\0'; i++)
h = h * 65599 + (unsigned char)x[i];
Faster!
return h & 1023;
}
What happens if
you mistakenly
write h & 1024?!
73
Speeding Up Key Comparisons!
Speeding up key comparisons!
For any non-trivial value comparison function!
Trick: store full hash result in structure!

int Table_search(struct Table *t,

const char *key, int *value) {
struct Node *p;
int h = hash(key); /* No % in hash function */
for (p = t->array[h%1024]; p != NULL; p = p->next)
if ((p->hash == h) && strcmp(p->key, key) == 0) {
*value = p->value;
return 1;
}
return 0; Why is this so
}
much faster?!

74