Hash Table and Hash Set

Hash table

Three ways to create hash tables:

library(hashtable)
h1 = hash_table(letters, 1:26)
h2 = hash_fm_table(letters, 1:26)
h3 = hash_env_table(letters, 1:26)
h1

## A hash table [hash_unordered_map] with 26 key-value (integer) pairs
##   z => 26
##   y => 25
##   x => 24
##   ......
##   c => 3
##   b => 2
##   a => 1

h2

## A hash table [hash_fm_table] with 26 key-value (integer) pairs
##   a => 1
##   b => 2
##   c => 3
##   ......
##   x => 24
##   y => 25
##   z => 26

h3

## A hash table [hash_env_table] with 26 key-value (integer) pairs
##   i => 9
##   j => 10
##   k => 11
##   ......
##   f => 6
##   g => 7
##   h => 8

The user interfaces for the two methods are the same. We only demonstrate using h1.

Get all keys:

hash_keys(h1)

##  [1] "z" "y" "x" "w" "v" "u" "t" "s" "q" "p" "o" "n" "m" "r" "l" "k" "j" "i" "h"
## [20] "g" "f" "e" "d" "c" "b" "a"

Get all values:

hash_values(h1)

##  [1] 26 25 24 23 22 21 20 19 17 16 15 14 13 18 12 11 10  9  8  7  6  5  4  3  2
## [26]  1

Get a subset of values by specifying keys:

hash_values(h1, c("a", "b", "c"))

## [1] 1 2 3

Get a single value using $, [[ or [:

h1$a

## [1] 1

h1[["a"]]

## [1] 1

h1[c("a", "b")]

## [1] 1 2

Test whether keys are in the hash table:

hash_exists(h1, c("a", "b", "foo"))

## [1]  TRUE  TRUE FALSE

Delete key-value pairs:

hash_delete(h1, c("a", "b"))
hash_exists(h1, c("a", "b"))

## [1] FALSE FALSE

Insert new key-value pairs, or modify key-value pairs if they already exist:

hash_insert(h1, "c", 100L); h1$c

## [1] 100

hash_insert(h1, "c", -1L); h1$c

## [1] -1

hash_insert(h1, "foo", 0L); h1$foo

## [1] 0

Insert or modify key-value pairs using $<-, [[<- or [<-:

h1$a = 20L; h1$a

## [1] 20

h1[["bar"]] = -100L; h1$bar

## [1] -100

h1[c("c", "d", "e")] = c(-1L, -2L, -3L); h1[c("c", "d", "e")]

## [1] -1 -2 -3

In previous examples, values are atomic vectors. It is basically the same if values are more general list.

h1 = hash_table(c("a", "b"), list(1L, "text"))
h1

## A hash table [hash_unordered_map] with 2 key-value (list) pairs
##   b => character [1] text
##   a => integer [1] 1

h1$c = 3.14
h1$d = lm(1~1) # an lm object
h1

## A hash table [hash_unordered_map] with 4 key-value (list) pairs
##   c => numeric [1] 3.14
##   b => character [1] text
##   d => complex value (lm)
##   a => integer [1] 1

Convert between hash table and named vector or list:

h1 = hash_table(c("a", "b"), 1:2)
as.vector(h1)

## b a 
## 2 1

h1 = hash_table(c("a", "b"), list(1L, "text"))
as.vector(h1)

## $b
## [1] "text"
## 
## $a
## [1] 1

vec = structure(1:2, names = c("a", "b"))
as.hash_table(vec)

## A hash table [hash_unordered_map] with 2 key-value (integer) pairs
##   b => 2
##   a => 1

lt = structure(list(1L, "text"), names = c("a", "b"))
as.hash_table(lt)

## A hash table [hash_unordered_map] with 2 key-value (list) pairs
##   b => character [1] text
##   a => integer [1] 1

Hash set

Hash sets are hash tables with no value associated. There are also three ways to create hash sets.

h1 = hash_set(letters)
h2 = hash_fm_set(letters)
h3 = hash_env_set(letters)
h1

## A hash set [hash_unordered_set] with 26 keys

Get all keys:

hash_keys(h1)

##  [1] "z" "y" "x" "w" "v" "u" "t" "s" "q" "p" "o" "n" "m" "r" "l" "k" "j" "i" "h"
## [20] "g" "f" "e" "d" "c" "b" "a"

Hash set has no value associated, so calling hash_value() throws an error.

hash_values(h1)

## Error in hash_values(h1): hash_unordered_set has no values.

Test whether keys are in the hash set:

hash_exists(h1, c("a", "foo"))

## [1]  TRUE FALSE

Add new keys:

hash_insert(h1, "foo")
hash_exists(h1, "foo")

## [1] TRUE

Delete keys:

hash_delete(h1, "foo")
hash_exists(h1, "foo")

## [1] FALSE

Hash sets are basically used to test whether keys exist, so we let $, [[ and [ to return TRUE or FALSE to represent whether keys exist.

h1$a

## [1] TRUE

h1[["a"]]

## [1] TRUE

h1$foo

## [1] FALSE

h1[c("a", "b", "foo")]

## [1]  TRUE  TRUE FALSE

If assigning TRUE, new keys are added to the hash set (if they do not exist), and if assigning FALSE, corresponding keys are deleted.

h1$a = FALSE
hash_exists(h1, "a")

## [1] FALSE

h1$foo = TRUE
hash_exists(h1, "foo")

## [1] TRUE

Convert between vectors (where elements are unique) and hash sets:

as.vector(h1)

##  [1] "z"   "y"   "foo" "x"   "w"   "v"   "u"   "t"   "s"   "q"   "p"   "o"  
## [13] "n"   "m"   "r"   "l"   "k"   "j"   "i"   "h"   "g"   "f"   "e"   "d"  
## [25] "c"   "b"

as.hash_set(letters)

## A hash set [hash_unordered_set] with 26 keys

hash_fm_table and hash_fm_set

Although sharing the same user interface, the hash table created by hash_fm_table() allows to modify the values if corresponding keys already exist.

h = hash_fm_table(letters, 1:26)
h$a = 100L

But it does not allow to delete or create key-value pairs.

h$foo = 1L  # insert new key foo

## Error in .local(h, keys, ...): hash_fm_table is not allowed to insert new keys.

hash_delete(h, "a")

## Error in hash_delete(h, "a"): hash_fm is not allowed to modify.

The hash set created by hash_fm_set() does not allow to delete or create keys.

h = hash_fm_set(letters)
h$a = FALSE

## Error in hash_delete(x, i): hash_fm is not allowed to modify.

h$foo = TRUE

## Error in .local(h, keys, ...): hash_fm_set is not allowed to modify.

Session info

sessionInfo()

## R version 4.3.3 (2024-02-29)
## Platform: x86_64-apple-darwin20 (64-bit)
## Running under: macOS 26.5.1
## 
## Matrix products: default
## BLAS:   /Library/Frameworks/R.framework/Versions/4.3-x86_64/Resources/lib/libRblas.0.dylib 
## LAPACK: /Library/Frameworks/R.framework/Versions/4.3-x86_64/Resources/lib/libRlapack.dylib;  LAPACK version 3.11.0
## 
## locale:
## [1] C/zh_CN.UTF-8/zh_CN.UTF-8/C/zh_CN.UTF-8/zh_CN.UTF-8
## 
## time zone: Europe/Berlin
## tzcode source: internal
## 
## attached base packages:
## [1] stats     graphics  grDevices utils     datasets  methods   base     
## 
## other attached packages:
## [1] hashtable_1.0.0
## 
## loaded via a namespace (and not attached):
##  [1] digest_0.6.35     R6_2.5.1          fastmatch_1.1-4   fastmap_1.1.1    
##  [5] xfun_0.43         cachem_1.0.8      knitr_1.45        htmltools_0.5.8.1
##  [9] rmarkdown_2.26    lifecycle_1.0.4   cli_3.6.2         sass_0.4.9       
## [13] jquerylib_0.1.4   compiler_4.3.3    tools_4.3.3       evaluate_0.23    
## [17] bslib_0.7.0       Rcpp_1.0.12       yaml_2.3.8        rlang_1.1.3      
## [21] jsonlite_1.8.8