1
0
mirror of https://github.com/fumiama/paper-manager.git synced 2026-06-04 23:40:24 +08:00

add jieba

This commit is contained in:
源文雨
2023-03-30 23:26:37 +08:00
parent 05e59426cd
commit 0ad433e9ce
5 changed files with 172 additions and 11 deletions

View File

@@ -1,9 +1,14 @@
package global
import (
"bytes"
"crypto/md5"
"encoding/binary"
"encoding/hex"
"encoding/json"
"errors"
"fmt"
"image"
"io"
"os"
"regexp"
@@ -11,6 +16,13 @@ import (
"strings"
"time"
_ "image/jpeg"
_ "image/png"
_ "golang.org/x/image/webp"
"github.com/corona10/goimagehash"
base14 "github.com/fumiama/go-base16384"
"github.com/fumiama/go-docx"
)
@@ -175,12 +187,12 @@ type File struct {
// AddFile from FileFolder+tempath and copy it to File.Path.
// The para res must belong to a valid user
func (f *FileDatabase) AddFile(tempath string, reg *Regex) (*File, error) {
func (f *FileDatabase) AddFile(tempath string, reg *Regex, istemp bool, progress func(uint)) (*File, error) {
user, err := UserDB.GetUserByID(reg.ID)
if err != nil {
return nil, err
}
if !user.IsFileManager() {
if !user.IsFileManager() && !istemp {
return nil, ErrInvalidRole
}
if strings.Contains(tempath, "..") {
@@ -212,6 +224,7 @@ func (f *FileDatabase) AddFile(tempath string, reg *Regex) (*File, error) {
if err != nil {
return nil, err
}
doc.Document.Body.DropDrawingOf("NilPicture")
majorre, err := regexp.Compile(reg.Major)
if err != nil {
return nil, err
@@ -220,6 +233,7 @@ func (f *FileDatabase) AddFile(tempath string, reg *Regex) (*File, error) {
if len(docs) < 2 {
return nil, ErrMajorSplitsTooShort
}
// filling File struct
file := &File{
ID: id,
UID: *user.ID,
@@ -307,7 +321,85 @@ func (f *FileDatabase) AddFile(tempath string, reg *Regex) (*File, error) {
}
}
docs = docs[1:]
// parse questions
subre, err := regexp.Compile(reg.Sub)
if err != nil {
return nil, err
}
for _, majordoc := range docs {
majorq := QuestionJSON{}
for _, it := range majordoc.Document.Body.Items {
if p, ok := it.(*docx.Paragraph); ok {
text := p.String()
majorinfo := majorre.FindStringSubmatch(text)
if len(majorinfo) >= 6 {
name, points := majorinfo[2], majorinfo[5]
majorq.Name = name
majorq.Points, _ = strconv.Atoi(points)
}
}
}
subdocs := majordoc.SplitByParagraph(docx.SplitDocxByPlainTextRegex(subre))
majorq.Sub = make([]QuestionJSON, 0, len(subdocs))
for _, subdoc := range subdocs {
sb := bytes.NewBuffer(make([]byte, 0, 4096))
for _, it := range subdoc.Document.Body.Items {
sb.WriteString(fmt.Sprint(it))
}
m := md5.Sum(sb.Bytes())
que := &Question{
ID: binary.LittleEndian.Uint64(m[:8]),
Plain: base14.BytesToString(sb.Bytes()),
Images: func() []byte {
m := make(map[string]string)
_ = subdoc.RangeRelationships(func(r *docx.Relationship) error {
if r.Type != docx.REL_IMAGE {
return nil
}
if r.Target == "" {
return nil
}
i := strings.LastIndex(r.Target, "/")
if i < 0 {
return nil
}
name := r.Target[i+1:]
if name == "" {
return nil
}
md := subdoc.Media(name)
if md == nil {
return nil
}
img, _, err := image.Decode(bytes.NewReader(md.Data))
if err != nil {
return nil
}
dh, err := goimagehash.DifferenceHash(img)
if err != nil {
return nil
}
var buf [8]byte
binary.LittleEndian.PutUint64(buf[:], dh.GetHash())
m[name] = hex.EncodeToString(buf[:])
return nil
})
if len(m) == 0 {
return nil
}
data, err := json.Marshal(m)
if err != nil {
return nil
}
return data
}(),
Vector: func() []byte {
plain := base14.BytesToString(sb.Bytes())
}(),
}
}
}
return file, nil
}
@@ -322,8 +414,7 @@ type QuestionJSON struct {
type Question struct {
ID uint64 // ID is the first 8 bytes of the Plain's md5
Plain string // Plain is the plain text of the question (like markdown format)
XML []byte // XML is the OpenXML bytes of the question
Images []byte // Images is json of the image paths in XML, ex. ['md5.jpg', 'md5.png', ...]
Images []byte // Images is json of the image dhash in XML, ex. ['rId1': '1234567890abcdef', ...]
Vector []byte // Vector is json of {word: rate, ...} freq
Dup []byte // Dup is json of Duplication struct
}

BIN
backend/utils/dict.zip Normal file

Binary file not shown.

29
backend/utils/jieba.go Normal file
View File

@@ -0,0 +1,29 @@
package utils
import (
"archive/zip"
"bytes"
_ "embed"
"github.com/fumiama/jieba"
)
//go:embed dict.zip
var dictzip []byte
// Segmenter jieba 分词器
var Segmenter = func() *jieba.Segmenter {
r, err := zip.NewReader(bytes.NewReader(dictzip), int64(len(dictzip)))
if err != nil {
panic(err)
}
f, err := r.Open("dict.txt")
if err != nil {
panic(err)
}
seg, err := jieba.LoadDictionary(f)
if err != nil {
panic(err)
}
return seg
}()

10
go.mod
View File

@@ -6,18 +6,22 @@ require (
github.com/FloatTech/sqlite v1.6.0
github.com/FloatTech/ttl v0.0.0-20220715042055-15612be72f5b
github.com/RomiChan/syncx v0.0.0-20221202055724-5f842c53020e
github.com/corona10/goimagehash v1.1.0
github.com/fumiama/go-base16384 v1.6.4
github.com/fumiama/go-docx v0.0.0-20230310052825-daf7190ea69b
github.com/fumiama/go-docx v0.0.0-20230330141738-34f53a967c03
github.com/fumiama/imgsz v0.0.2
github.com/fumiama/jieba v0.0.0-20221203025406-36c17a10b565
github.com/sirupsen/logrus v1.9.0
golang.org/x/image v0.6.0
)
require (
github.com/google/uuid v1.3.0 // indirect
github.com/mattn/go-isatty v0.0.16 // indirect
github.com/nfnt/resize v0.0.0-20180221191011-83c6a9932646 // indirect
github.com/remyoudompheng/bigfft v0.0.0-20200410134404-eec4a21b6bb0 // indirect
golang.org/x/sys v0.0.0-20220811171246-fbc7d0a398ab // indirect
golang.org/x/text v0.3.7 // indirect
golang.org/x/sys v0.5.0 // indirect
golang.org/x/text v0.8.0 // indirect
modernc.org/libc v1.21.5 // indirect
modernc.org/mathutil v1.5.0 // indirect
modernc.org/memory v1.4.0 // indirect

45
go.sum
View File

@@ -4,6 +4,8 @@ github.com/FloatTech/ttl v0.0.0-20220715042055-15612be72f5b h1:tvciXWq2nuvTbFeJG
github.com/FloatTech/ttl v0.0.0-20220715042055-15612be72f5b/go.mod h1:fHZFWGquNXuHttu9dUYoKuNbm3dzLETnIOnm1muSfDs=
github.com/RomiChan/syncx v0.0.0-20221202055724-5f842c53020e h1:wR3MXQ3VbUlPKOOUwLOYgh/QaJThBTYtsl673O3lqSA=
github.com/RomiChan/syncx v0.0.0-20221202055724-5f842c53020e/go.mod h1:vD7Ra3Q9onRtojoY5sMCLQ7JBgjUsrXDnDKyFxqpf9w=
github.com/corona10/goimagehash v1.1.0 h1:teNMX/1e+Wn/AYSbLHX8mj+mF9r60R1kBeqE9MkoYwI=
github.com/corona10/goimagehash v1.1.0/go.mod h1:VkvE0mLn84L4aF8vCb6mafVajEb6QYMHl2ZJLn0mOGI=
github.com/davecgh/go-spew v1.1.0/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
github.com/davecgh/go-spew v1.1.1 h1:vj9j/u1bqnvCEfJOwUhtlOARqs3+rkHYY13jYWTU97c=
github.com/davecgh/go-spew v1.1.1/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
@@ -11,16 +13,20 @@ github.com/fumiama/bigfft v0.0.0-20211011143303-6e0bfa3c836b h1:Zt3pFQditAdWTHCO
github.com/fumiama/bigfft v0.0.0-20211011143303-6e0bfa3c836b/go.mod h1:qqbHyh8v60DhA7CoWK5oRCqLrMHRGoxYCSS9EjAz6Eo=
github.com/fumiama/go-base16384 v1.6.4 h1:rYDRwD/th2cG4U7QLokpzmST1cCxZGXtHmolOUePt5o=
github.com/fumiama/go-base16384 v1.6.4/go.mod h1:OEn+947GV5gsbTAnyuUW/SrfxJYUdYupSIQXOuGOcXM=
github.com/fumiama/go-docx v0.0.0-20230310052825-daf7190ea69b h1:1KYtEitNxRbh+O8mgGlji4nQKzf7SQHYxiuqDAwRCc8=
github.com/fumiama/go-docx v0.0.0-20230310052825-daf7190ea69b/go.mod h1:ssRF0IaB1hCcKIObp3FkZOsjTcAHpgii70JelNb4H8M=
github.com/fumiama/go-docx v0.0.0-20230330141738-34f53a967c03 h1:gQ9cMYk9QhTXh5sx74RwuNoDzJqVLYfOBsl/0rMMDns=
github.com/fumiama/go-docx v0.0.0-20230330141738-34f53a967c03/go.mod h1:ssRF0IaB1hCcKIObp3FkZOsjTcAHpgii70JelNb4H8M=
github.com/fumiama/imgsz v0.0.2 h1:fAkC0FnIscdKOXwAxlyw3EUba5NzxZdSxGaq3Uyfxak=
github.com/fumiama/imgsz v0.0.2/go.mod h1:dR71mI3I2O5u6+PCpd47M9TZptzP+39tRBcbdIkoqM4=
github.com/fumiama/jieba v0.0.0-20221203025406-36c17a10b565 h1:sQuR2+N5HurnvsZhiKdEg+Ig354TaqgCQRxd/0KgIOQ=
github.com/fumiama/jieba v0.0.0-20221203025406-36c17a10b565/go.mod h1:UUEvyLTJ7yoOA/viKG4wEis4ERydM7+Ny6gZUWgkS80=
github.com/fumiama/sqlite3 v1.20.0-with-win386 h1:ZR1AXGBEtkfq9GAXehOVcwn+aaCG8itrkgEsz4ggx5k=
github.com/fumiama/sqlite3 v1.20.0-with-win386/go.mod h1:Os58MHwYCcYZCy2PGChBrQtBAw5/LS1ZZOkfc+C/I7s=
github.com/google/uuid v1.3.0 h1:t6JiXgmwXMjEs8VusXIJk2BXHsn+wx8BZdTaoZ5fu7I=
github.com/google/uuid v1.3.0/go.mod h1:TIyPZe4MgqvfeYDBFedMoGGpEw/LqOeaOT+nhxU+yHo=
github.com/mattn/go-isatty v0.0.16 h1:bq3VjFmv/sOjHtdEhmkEV4x1AJtvUvOJ2PFAZ5+peKQ=
github.com/mattn/go-isatty v0.0.16/go.mod h1:kYGgaQfpe5nmfYZH+SKPsOc2e4SrIfOl2e/yFXSvRLM=
github.com/nfnt/resize v0.0.0-20180221191011-83c6a9932646 h1:zYyBkD/k9seD2A7fsi6Oo2LfFZAehjjQMERAvZLEDnQ=
github.com/nfnt/resize v0.0.0-20180221191011-83c6a9932646/go.mod h1:jpp1/29i3P1S/RLdc7JQKbRpFeM1dOBd8T9ki5s+AY8=
github.com/pmezard/go-difflib v1.0.0 h1:4DBwDE0NGyQoBHbLQYPwSUPoCMWR5BEzIk/f1lZbAQM=
github.com/pmezard/go-difflib v1.0.0/go.mod h1:iKH77koFhYxTK1pcRnkKkqfTogsbg7gZNVY4sRDYZ/4=
github.com/sirupsen/logrus v1.9.0 h1:trlNQbNUG3OdDrDil03MCb1H2o9nJ1x4/5LYw7byDE0=
@@ -29,12 +35,43 @@ github.com/stretchr/objx v0.1.0/go.mod h1:HFkY916IF+rwdDfMAkV7OtwuqBVzrE8GR6GFx+
github.com/stretchr/testify v1.7.0/go.mod h1:6Fq8oRcR53rry900zMqJjRRixrwX3KX962/h/Wwjteg=
github.com/stretchr/testify v1.7.1/go.mod h1:6Fq8oRcR53rry900zMqJjRRixrwX3KX962/h/Wwjteg=
github.com/stretchr/testify v1.8.0 h1:pSgiaMZlXftHpm5L7V1+rVB+AZJydKsMxsQBIJw4PKk=
github.com/yuin/goldmark v1.4.13/go.mod h1:6yULJ656Px+3vBD8DxQVa3kxgyrAnzto9xy5taEt/CY=
golang.org/x/crypto v0.0.0-20190308221718-c2843e01d9a2/go.mod h1:djNgcEr1/C05ACkg1iLfiJU5Ep61QUkGW8qpdssI0+w=
golang.org/x/crypto v0.0.0-20210921155107-089bfa567519/go.mod h1:GvvjBRRGRdwPK5ydBHafDWAxML/pGHZbMvKqRZ5+Abc=
golang.org/x/image v0.6.0 h1:bR8b5okrPI3g/gyZakLZHeWxAR8Dn5CyxXv1hLH5g/4=
golang.org/x/image v0.6.0/go.mod h1:MXLdDR43H7cDJq5GEGXEVeeNhPgi+YYEQ2pC1byI1x0=
golang.org/x/mod v0.6.0-dev.0.20220419223038-86c51ed26bb4/go.mod h1:jJ57K6gSWd91VN4djpZkiMVwK6gcyfeH4XE8wZrZaV4=
golang.org/x/mod v0.8.0/go.mod h1:iBbtSCu2XBx23ZKBPSOrRkjjQPZFPuis4dIYUhu/chs=
golang.org/x/net v0.0.0-20190620200207-3b0461eec859/go.mod h1:z5CRVTTTmAJ677TzLLGU+0bjPO0LkuOLi4/5GtJWs/s=
golang.org/x/net v0.0.0-20210226172049-e18ecbb05110/go.mod h1:m0MpNAwzfU5UDzcl9v0D8zg8gWTRqZa9RBIspLL5mdg=
golang.org/x/net v0.0.0-20220722155237-a158d28d115b/go.mod h1:XRhObCWvk6IyKnWLug+ECip1KBveYUHfp+8e9klMJ9c=
golang.org/x/net v0.6.0/go.mod h1:2Tu9+aMcznHK/AK1HMvgo6xiTLG5rD5rZLDS+rp2Bjs=
golang.org/x/sync v0.0.0-20190423024810-112230192c58/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
golang.org/x/sync v0.0.0-20220722155255-886fb9371eb4/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
golang.org/x/sync v0.1.0/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
golang.org/x/sys v0.0.0-20190215142949-d0b11bdaac8a/go.mod h1:STP8DvDyc/dI5b8T5hshtkjS+E42TnysNCUPdjciGhY=
golang.org/x/sys v0.0.0-20201119102817-f84b799fce68/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
golang.org/x/sys v0.0.0-20210615035016-665e8c7367d1/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
golang.org/x/sys v0.0.0-20220520151302-bc2c85ada10a/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
golang.org/x/sys v0.0.0-20220715151400-c0bba94af5f8/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
golang.org/x/sys v0.0.0-20220811171246-fbc7d0a398ab h1:2QkjZIsXupsJbJIdSjjUOgWK3aEtzyuh2mPt3l/CkeU=
golang.org/x/sys v0.0.0-20220722155257-8c9f86f7a55f/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
golang.org/x/sys v0.0.0-20220811171246-fbc7d0a398ab/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
golang.org/x/text v0.3.7 h1:olpwvP2KacW1ZWvsR7uQhoyTYvKAupfQrRGBFM352Gk=
golang.org/x/sys v0.5.0 h1:MUK/U/4lj1t1oPg0HfuXDN/Z1wv31ZJ/YcPiGccS4DU=
golang.org/x/sys v0.5.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
golang.org/x/term v0.0.0-20201126162022-7de9c90e9dd1/go.mod h1:bj7SfCRtBDWHUb9snDiAeCFNEtKQo2Wmx5Cou7ajbmo=
golang.org/x/term v0.0.0-20210927222741-03fcf44c2211/go.mod h1:jbD1KX2456YbFQfuXm/mYQcufACuNUgVhRMnK/tPxf8=
golang.org/x/term v0.5.0/go.mod h1:jMB1sMXY+tzblOD4FWmEbocvup2/aLOaQEp7JmGp78k=
golang.org/x/text v0.3.0/go.mod h1:NqM8EUOU14njkJ3fqMW+pc6Ldnwhi/IjpwHt7yyuwOQ=
golang.org/x/text v0.3.3/go.mod h1:5Zoc/QRtKVWzQhOtBMvqHzDpF6irO9z98xDceosuGiQ=
golang.org/x/text v0.3.7/go.mod h1:u+2+/6zg+i71rQMx5EYifcz6MCKuco9NR6JIITiCfzQ=
golang.org/x/text v0.7.0/go.mod h1:mrYo+phRRbMaCq/xk9113O4dZlRixOauAjOtrjsXDZ8=
golang.org/x/text v0.8.0 h1:57P1ETyNKtuIjB4SRd15iJxuhj8Gc416Y78H3qgMh68=
golang.org/x/text v0.8.0/go.mod h1:e1OnstbJyHTd6l/uOt8jFFHp6TRDWZR/bV3emEE/zU8=
golang.org/x/tools v0.0.0-20180917221912-90fa682c2a6e/go.mod h1:n7NCudcB/nEzxVGmLbDWY5pfWTLqBcC2KZ6jyYvM4mQ=
golang.org/x/tools v0.0.0-20191119224855-298f0cb1881e/go.mod h1:b+2E5dAYhXwXZwtnZ6UAqBI28+e2cm9otk0dWdXHAEo=
golang.org/x/tools v0.1.12/go.mod h1:hNGJHUnrk76NpqgfD5Aqm5Crs+Hm0VOH/i9J2+nxYbc=
golang.org/x/tools v0.6.0/go.mod h1:Xwgl3UAJ/d3gWutnCtw505GrjyAbvKui8lOU390QaIU=
golang.org/x/xerrors v0.0.0-20190717185122-a985d3407aa7/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=
gopkg.in/check.v1 v0.0.0-20161208181325-20d25e280405/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0=
gopkg.in/yaml.v3 v3.0.0-20200313102051-9f266ea9e77c/go.mod h1:K4uyk7z7BCEPqu6E+C64Yfv1cQ7kz7rIZviUmN+EgEM=
gopkg.in/yaml.v3 v3.0.1 h1:fxVm/GzAzEWqLHuvctI91KS9hhNmmWOoWu0XTYJS7CA=