mirror/v
1
0
Fork 0
mirror of https://github.com/vlang/v.git synced 2023-08-10 21:13:21 +03:00
Code Issues Projects Releases Wiki Activity

run vfmt on more files

Browse Source
This commit is contained in:
Alexander Medvednikov
2019-12-18 21:56:30 +03:00
parent 1cef83aea4
commit df2f98e276
8 changed files with 403 additions and 320 deletions
Download Patch File Download Diff File Expand all files Collapse all files

38
vlib/strings/similarity.v
View File

@ -1,20 +1,21 @@
module strings
#-js
//#-js
// use levenshtein distance algorithm to calculate
// the distance between between two strings (lower is closer)
pub fn levenshtein_distance(a, b string) int {
mut f := [0].repeat(b.len+1)
mut f := [0].repeat(b.len + 1)
for ca in a {
mut j := 1
mut fj1 := f[0]
f[0]++
for cb in b {
mut mn := if f[j]+1 <= f[j-1]+1 { f[j]+1 } else { f[j-1]+1 }
mut mn := if f[j] + 1 <= f[j - 1] + 1 { f[j] + 1 } else { f[j - 1] + 1 }
if cb != ca {
mn = if mn <= fj1+1 { mn } else { fj1+1 }
} else {
mn = if mn <= fj1 + 1 { mn } else { fj1 + 1 }
}
else {
mn = if mn <= fj1 { mn } else { fj1 }
}
fj1 = f[j]
@ -22,7 +23,7 @@ pub fn levenshtein_distance(a, b string) int {
j++
}
}
return f[f.len-1]
return f[f.len - 1]
}
// use levenshtein distance algorithm to calculate
@ -30,28 +31,33 @@ pub fn levenshtein_distance(a, b string) int {
pub fn levenshtein_distance_percentage(a, b string) f32 {
d := levenshtein_distance(a, b)
l := if a.len >= b.len { a.len } else { b.len }
return (1.00 - f32(d)/f32(l)) * 100.00
return (1.00 - f32(d) / f32(l)) * 100.00
}
// implementation of Sørensen–Dice coefficient.
// find the similarity between two strings.
// returns coefficient between 0.0 (not similar) and 1.0 (exact match).
pub fn dice_coefficient(s1, s2 string) f32 {
if s1.len == 0 || s2.len == 0 { return 0.0 }
if s1 == s2 { return 1.0 }
if s1.len < 2 || s2.len < 2 { return 0.0 }
if s1.len == 0 || s2.len == 0 {
return 0.0
}
if s1 == s2 {
return 1.0
}
if s1.len < 2 || s2.len < 2 {
return 0.0
}
a := if s1.len > s2.len { s1 } else { s2 }
b := if a == s1 { s2 } else { s1 }
mut first_bigrams := map[string]int
for i := 0; i < a.len-1; i++ {
bigram := a[i..i+2]
q := if bigram in first_bigrams {
first_bigrams[bigram]+1 } else { 1 }
for i := 0; i < a.len - 1; i++ {
bigram := a[i..i + 2]
q := if bigram in first_bigrams { first_bigrams[bigram] + 1 } else { 1 }
first_bigrams[bigram] = q
}
mut intersection_size := 0
for i := 0; i < b.len-1; i++ {
bigram := b[i..i+2]
for i := 0; i < b.len - 1; i++ {
bigram := b[i..i + 2]
count := if bigram in first_bigrams { first_bigrams[bigram] } else { 0 }
if count > 0 {
first_bigrams[bigram] = count - 1