addrkit
3be331bb65
- domain: address normalization/parsing, matching with explicit statuses - adapters: SQLite registry store, ArcGIS outages client, optional LLM rewriter, HTTP API - seed pipeline with duplicate handling and unparsed reporting - CLI (seed/verify/resolve), systemd unit, OpenAPI contract, tests
63 lines
1.2 KiB
Go
63 lines
1.2 KiB
Go
package match
|
|
|
|
// levenshtein returns the edit distance between two strings, measured in
|
|
// runes. It uses the rolling-row formulation: O(min(n,m)) memory.
|
|
//
|
|
// The resolver uses it only to tolerate typos in the *street name*; house
|
|
// numbers are always compared exactly, because a wrong house is worse than a
|
|
// missing one.
|
|
func levenshtein(a, b string) int {
|
|
ra, rb := []rune(a), []rune(b)
|
|
if len(ra) == 0 {
|
|
return len(rb)
|
|
}
|
|
if len(rb) == 0 {
|
|
return len(ra)
|
|
}
|
|
prev := make([]int, len(rb)+1)
|
|
curr := make([]int, len(rb)+1)
|
|
for j := range prev {
|
|
prev[j] = j
|
|
}
|
|
for i := 1; i <= len(ra); i++ {
|
|
curr[0] = i
|
|
for j := 1; j <= len(rb); j++ {
|
|
cost := 1
|
|
if ra[i-1] == rb[j-1] {
|
|
cost = 0
|
|
}
|
|
curr[j] = min3(prev[j]+1, curr[j-1]+1, prev[j-1]+cost)
|
|
}
|
|
prev, curr = curr, prev
|
|
}
|
|
return prev[len(rb)]
|
|
}
|
|
|
|
// ratio returns a 0..1 similarity where 1 means identical. It is
|
|
// 1 - distance/max(len), which is stable and easy to reason about.
|
|
func ratio(a, b string) float64 {
|
|
if a == b {
|
|
return 1
|
|
}
|
|
la, lb := len([]rune(a)), len([]rune(b))
|
|
m := la
|
|
if lb > m {
|
|
m = lb
|
|
}
|
|
if m == 0 {
|
|
return 1
|
|
}
|
|
return 1 - float64(levenshtein(a, b))/float64(m)
|
|
}
|
|
|
|
func min3(a, b, c int) int {
|
|
m := a
|
|
if b < m {
|
|
m = b
|
|
}
|
|
if c < m {
|
|
m = c
|
|
}
|
|
return m
|
|
}
|