优化 dict, add fs.File 支持

posseg/dictionary.go

@@ -1,6 +1,7 @@
 package posseg
 
 import (
+	"io/fs"
 	"math"
 	"sync"
 
@@ -69,6 +70,10 @@ func (d *Dictionary) Pos(key string) (string, bool) {
 	return pos, ok
 }
 
-func (d *Dictionary) loadDictionary(fileName string) error {
-	return dictionary.LoadDictionary(d, fileName)
+func (d *Dictionary) loadDictionary(file fs.File) error {
+	return dictionary.LoadDictionary(d, file)
+}
+
+func (d *Dictionary) loadDictionaryAt(file string) error {
+	return dictionary.LoadDictionaryAt(d, file)
 }

posseg/example_test.go

@@ -8,7 +8,7 @@ import (
 
 func Example() {
 	var seg posseg.Segmenter
-	seg.LoadDictionary("../dict.txt")
+	seg.LoadDictionaryAt("../dict.txt")
 
 	for segment := range seg.Cut("我爱北京天安门", true) {
 		fmt.Printf("%s %s\n", segment.Text(), segment.Pos())

posseg/posseg.go

@@ -2,6 +2,7 @@
 package posseg
 
 import (
+	"io/fs"
 	"math"
 	"regexp"
 
@@ -39,17 +40,31 @@ type Segmenter struct {
 }
 
 // LoadDictionary loads dictionary from given file name.
-// Everytime LoadDictionary is called, previously loaded dictionary will be cleard.
-func (seg *Segmenter) LoadDictionary(fileName string) error {
+// Everytime LoadDictionaryAt is called, previously loaded dictionary will be cleard.
+func (seg *Segmenter) LoadDictionary(file fs.File) error {
 	seg.dict = &Dictionary{freqMap: make(map[string]float64), posMap: make(map[string]string)}
-	return seg.dict.loadDictionary(fileName)
+	return seg.dict.loadDictionary(file)
+}
+
+// LoadDictionaryAt loads dictionary from given file name.
+// Everytime LoadDictionaryAt is called, previously loaded dictionary will be cleard.
+func (seg *Segmenter) LoadDictionaryAt(fileName string) error {
+	seg.dict = &Dictionary{freqMap: make(map[string]float64), posMap: make(map[string]string)}
+	return seg.dict.loadDictionaryAt(fileName)
 }
 
 // LoadUserDictionary loads a user specified dictionary, it must be called
 // after LoadDictionary, and it will not clear any previous loaded dictionary,
 // instead it will override exist entries.
-func (seg *Segmenter) LoadUserDictionary(fileName string) error {
-	return seg.dict.loadDictionary(fileName)
+func (seg *Segmenter) LoadUserDictionary(file fs.File) error {
+	return seg.dict.loadDictionary(file)
+}
+
+// LoadUserDictionaryAt loads a user specified dictionary, it must be called
+// after LoadDictionary, and it will not clear any previous loaded dictionary,
+// instead it will override exist entries.
+func (seg *Segmenter) LoadUserDictionaryAt(fileName string) error {
+	return seg.dict.loadDictionaryAt(fileName)
 }
 
 func (seg *Segmenter) cutDetailInternal(sentence string) <-chan Segment {

posseg/posseg_test.go

@@ -269,7 +269,7 @@ var (
 )
 
 func init() {
-	seg.LoadDictionary("../dict.txt")
+	seg.LoadDictionaryAt("../dict.txt")
 }
 
 func chanToArray(ch <-chan Segment) []Segment {
@@ -357,8 +357,8 @@ func TestBug137(t *testing.T) {
 }
 
 func TestUserDict(t *testing.T) {
-	seg.LoadUserDictionary("../userdict.txt")
-	defer seg.LoadDictionary("../dict.txt")
+	seg.LoadUserDictionaryAt("../userdict.txt")
+	defer seg.LoadDictionaryAt("../dict.txt")
 	sentence := "李小福是创新办主任也是云计算方面的专家; 什么是八一双鹿例如我输入一个带“韩玉赏鉴”的标题，在自定义词库中也增加了此词为N类型"
 
 	cutResult := []Segment{