Making doc extraction more reliable (#17842)
* Making doc extraction more reliable * fix error message * Adding test doc file * Removing test that not works on CI because the lack of a binary Co-authored-by: Mattermod <mattermod@users.noreply.github.com>
Этот коммит содержится в:
коммит произвёл
GitHub
родитель
0f07a934ff
Коммит
b9cceb70ae
2
go.mod
2
go.mod
@@ -3,7 +3,7 @@ module github.com/mattermost/mattermost-server/v6
|
||||
go 1.15
|
||||
|
||||
require (
|
||||
code.sajari.com/docconv v1.1.1-0.20200701232649-d9ea05fbd50a
|
||||
code.sajari.com/docconv v1.1.1-0.20210427001343-7b3472bc323a
|
||||
github.com/HdrHistogram/hdrhistogram-go v0.9.0 // indirect
|
||||
github.com/Masterminds/semver/v3 v3.1.1
|
||||
github.com/Masterminds/squirrel v1.5.0
|
||||
|
||||
2
go.sum
2
go.sum
@@ -38,6 +38,8 @@ cloud.google.com/go/storage v1.8.0/go.mod h1:Wv1Oy7z6Yz3DshWRJFhqM/UCfaWIRTdp0RX
|
||||
cloud.google.com/go/storage v1.10.0/go.mod h1:FLPqc6j+Ki4BU591ie1oL6qBQGu2Bl/tZ9ullr3+Kg0=
|
||||
code.sajari.com/docconv v1.1.1-0.20200701232649-d9ea05fbd50a h1:e0dRHyAfGcext3/lnwfsl81PKJRNgLyA843n72mPCes=
|
||||
code.sajari.com/docconv v1.1.1-0.20200701232649-d9ea05fbd50a/go.mod h1:DooS873W9YwUjTwEYGpg55aDlvnx1VcEdr7IJ9rEW8g=
|
||||
code.sajari.com/docconv v1.1.1-0.20210427001343-7b3472bc323a h1:AEvqb7V5SSC89lAp9UQd7ytVVLm6f4AQbtzr9lk0bFg=
|
||||
code.sajari.com/docconv v1.1.1-0.20210427001343-7b3472bc323a/go.mod h1:KPNt2zuWplps1W0TpOb6ltHj4Xu+j6h7a+YkqGHrxQE=
|
||||
contrib.go.opencensus.io/exporter/ocagent v0.4.9/go.mod h1:ueLzZcP7LPhPulEBukGn4aLh7Mx9YJwpVJ9nL2FYltw=
|
||||
dmitri.shuralyov.com/app/changes v0.0.0-20180602232624-0a106ad413e3/go.mod h1:Yl+fi1br7+Rr3LqpNJf1/uxUdtRUV+Tnj0o93V2B9MU=
|
||||
dmitri.shuralyov.com/gpu/mtl v0.0.0-20190408044501-666a987793e9/go.mod h1:H6x//7gZCb22OMCxBHrMx7a5I7Hp++hsVxbQ4BYO7hU=
|
||||
|
||||
@@ -150,7 +150,7 @@ func TestExtract(t *testing.T) {
|
||||
require.Equal(t, "", text)
|
||||
})
|
||||
|
||||
t.Run("Wrong extension", func(t *testing.T) {
|
||||
t.Run("Wrong docx extension", func(t *testing.T) {
|
||||
data, err := testutils.ReadTestFile("sample-doc.pdf")
|
||||
require.NoError(t, err)
|
||||
text, err := Extract("sample-doc.docx", bytes.NewReader(data), ExtractSettings{})
|
||||
|
||||
@@ -31,7 +31,14 @@ func (de *documentExtractor) Match(filename string) bool {
|
||||
return ok
|
||||
}
|
||||
|
||||
func (de *documentExtractor) Extract(filename string, r io.ReadSeeker) (string, error) {
|
||||
func (de *documentExtractor) Extract(filename string, r io.ReadSeeker) (out string, outErr error) {
|
||||
defer func() {
|
||||
if r := recover(); r != nil {
|
||||
out = ""
|
||||
outErr = errors.New("error extracting document text")
|
||||
}
|
||||
}()
|
||||
|
||||
extension := strings.TrimPrefix(path.Ext(filename), ".")
|
||||
converter, ok := doconvConverterByExtensions[extension]
|
||||
if !ok {
|
||||
|
||||
Двоичные данные
tests/sample-doc.doc
Обычный файл
Двоичные данные
tests/sample-doc.doc
Обычный файл
Двоичный файл не отображается.
10
vendor/code.sajari.com/docconv/.travis.yml
сгенерированный
поставляемый
10
vendor/code.sajari.com/docconv/.travis.yml
сгенерированный
поставляемый
@@ -1,10 +0,0 @@
|
||||
sudo: false
|
||||
language: go
|
||||
go:
|
||||
- "1.13"
|
||||
- "1.14"
|
||||
- tip
|
||||
go_import_path: code.sajari.com/docconv
|
||||
notifications:
|
||||
email:
|
||||
- infra@sajari.com
|
||||
8
vendor/code.sajari.com/docconv/README.md
сгенерированный
поставляемый
8
vendor/code.sajari.com/docconv/README.md
сгенерированный
поставляемый
@@ -1,11 +1,13 @@
|
||||
# docconv
|
||||
|
||||
[](https://godoc.org/code.sajari.com/docconv)
|
||||
[](https://travis-ci.org/sajari/docconv)
|
||||
[](https://pkg.go.dev/code.sajari.com/docconv)
|
||||
[](https://github.com/sajari/docconv/actions)
|
||||
[](https://goreportcard.com/report/code.sajari.com/docconv)
|
||||
[](https://sourcegraph.com/github.com/sajari/docconv)
|
||||
|
||||
A Go wrapper library to convert PDF, DOC, DOCX, XML, HTML, RTF, ODT, Pages documents and images (see optional dependencies below) to plain text.
|
||||
|
||||
> **Note for returning users:** the Go import path for this package been moved to `code.sajari.com/docconv`.
|
||||
> **Note for returning users:** the Go import path for this package changed to `code.sajari.com/docconv`.
|
||||
|
||||
## Installation
|
||||
|
||||
|
||||
1
vendor/code.sajari.com/docconv/go.mod
сгенерированный
поставляемый
1
vendor/code.sajari.com/docconv/go.mod
сгенерированный
поставляемый
@@ -10,6 +10,7 @@ require (
|
||||
github.com/araddon/dateparse v0.0.0-20200409225146-d820a6159ab1 // indirect
|
||||
github.com/go-resty/resty/v2 v2.3.0 // indirect
|
||||
github.com/golang/protobuf v1.4.2
|
||||
github.com/google/go-cmp v0.4.0
|
||||
github.com/jaytaylor/html2text v0.0.0-20200412013138-3577fbdbcff7 // indirect
|
||||
github.com/levigross/exp-html v0.0.0-20120902181939-8df60c69a8f5 // indirect
|
||||
github.com/mattn/go-runewidth v0.0.9 // indirect
|
||||
|
||||
9
vendor/code.sajari.com/docconv/go.sum
сгенерированный
поставляемый
9
vendor/code.sajari.com/docconv/go.sum
сгенерированный
поставляемый
@@ -1,17 +1,14 @@
|
||||
github.com/JalfResi/justext v0.0.0-20170829062021-c0282dea7198 h1:8P+AjBhGByCuCX2zTkAf6UY+dj0JczX+t6cSdCSyvfw=
|
||||
github.com/JalfResi/justext v0.0.0-20170829062021-c0282dea7198/go.mod h1:0SURuH1rsE8aVWvutuMZghRNrNrYEUzibzJfhEYR8L0=
|
||||
github.com/PuerkitoBio/goquery v1.4.1 h1:smcIRGdYm/w7JSbcdeLHEMzxmsBQvl8lhf0dSw2nzMI=
|
||||
github.com/PuerkitoBio/goquery v1.4.1/go.mod h1:T9ezsOHcCrDCgA8aF1Cqr3sSYbO/xgdy8/R/XiIMAhA=
|
||||
github.com/PuerkitoBio/goquery v1.5.1 h1:PSPBGne8NIUWw+/7vFBV+kG2J/5MOjbzc7154OaKCSE=
|
||||
github.com/PuerkitoBio/goquery v1.5.1/go.mod h1:GsLWisAFVj4WgDibEWF4pvYnkVQBpKBKeU+7zCJoLcc=
|
||||
github.com/advancedlogic/GoOse v0.0.0-20191112112754-e742535969c1 h1:d0Ct1dZwgwMO0Llf81Eu+Lyj6kwqXdqHP/WsSkEria0=
|
||||
github.com/advancedlogic/GoOse v0.0.0-20191112112754-e742535969c1/go.mod h1:f3HCSN1fBWjcpGtXyM119MJgeQl838v6so/PQOqvE1w=
|
||||
github.com/andybalholm/cascadia v1.0.0 h1:hOCXnnZ5A+3eVDX8pvgl4kofXv2ELss0bKcqRySc45o=
|
||||
github.com/andybalholm/cascadia v1.0.0/go.mod h1:GsXiBklL0woXo1j/WYWtSYYC4ouU9PqHO0sqidkEA4Y=
|
||||
github.com/andybalholm/cascadia v1.1.0/go.mod h1:GsXiBklL0woXo1j/WYWtSYYC4ouU9PqHO0sqidkEA4Y=
|
||||
github.com/andybalholm/cascadia v1.2.0 h1:vuRCkM5Ozh/BfmsaTm26kbjm0mIOM3yS5Ek/F5h18aE=
|
||||
github.com/andybalholm/cascadia v1.2.0/go.mod h1:YCyR8vOZT9aZ1CHEd8ap0gMVm2aFgxBp0T0eFw1RUQY=
|
||||
github.com/araddon/dateparse v0.0.0-20180729174819-cfd92a431d0e h1:s05JG2GwtJMHaPcXDpo4V35TFgyYZzNsmBlSkHPEbeg=
|
||||
github.com/araddon/dateparse v0.0.0-20180729174819-cfd92a431d0e/go.mod h1:SLqhdZcd+dF3TEVL2RMoob5bBP5R1P1qkox+HtCBgGI=
|
||||
github.com/araddon/dateparse v0.0.0-20200409225146-d820a6159ab1 h1:TEBmxO80TM04L8IuMWk77SGL1HomBmKTdzdJLLWznxI=
|
||||
github.com/araddon/dateparse v0.0.0-20200409225146-d820a6159ab1/go.mod h1:SLqhdZcd+dF3TEVL2RMoob5bBP5R1P1qkox+HtCBgGI=
|
||||
@@ -21,7 +18,6 @@ github.com/fatih/set v0.2.1 h1:nn2CaJyknWE/6txyUDGwysr3G5QC6xWB/PtVjPBbeaA=
|
||||
github.com/fatih/set v0.2.1/go.mod h1:+RKtMCH+favT2+3YecHGxcc0b4KyVWA1QWWJUs4E0CI=
|
||||
github.com/gigawattio/window v0.0.0-20180317192513-0f5467e35573 h1:u8AQ9bPa9oC+8/A/jlWouakhIvkFfuxgIIRjiy8av7I=
|
||||
github.com/gigawattio/window v0.0.0-20180317192513-0f5467e35573/go.mod h1:eBvb3i++NHDH4Ugo9qCvMw8t0mTSctaEa5blJbWcNxs=
|
||||
github.com/go-resty/resty/v2 v2.0.0 h1:9Nq/U+V4xsoDnDa/iTrABDWUCuk3Ne92XFHPe6dKWUc=
|
||||
github.com/go-resty/resty/v2 v2.0.0/go.mod h1:dZGr0i9PLlaaTD4H/hoZIDjQ+r6xq8mgbRzHZf7f2J8=
|
||||
github.com/go-resty/resty/v2 v2.3.0 h1:JOOeAvjSlapTT92p8xiS19Zxev1neGikoHsXJeOq8So=
|
||||
github.com/go-resty/resty/v2 v2.3.0/go.mod h1:UpN9CgLZNsv4e9XG50UU8xdI0F43UQ4HmxLBDwaroHU=
|
||||
@@ -36,18 +32,15 @@ github.com/google/go-cmp v0.3.0/go.mod h1:8QqcDgzrUqlUb/G2PQTWiueGozuR1884gddMyw
|
||||
github.com/google/go-cmp v0.3.1/go.mod h1:8QqcDgzrUqlUb/G2PQTWiueGozuR1884gddMywk6iLU=
|
||||
github.com/google/go-cmp v0.4.0 h1:xsAVV57WRhGj6kEIi8ReJzQlHHqcBYCElAvkovg3B/4=
|
||||
github.com/google/go-cmp v0.4.0/go.mod h1:v8dTdLbMG2kIc/vJvl+f65V22dbkXbowE6jgT/gNBxE=
|
||||
github.com/jaytaylor/html2text v0.0.0-20180606194806-57d518f124b0 h1:xqgexXAGQgY3HAjNPSaCqn5Aahbo5TKsmhp8VRfr1iQ=
|
||||
github.com/jaytaylor/html2text v0.0.0-20180606194806-57d518f124b0/go.mod h1:CVKlgaMiht+LXvHG173ujK6JUhZXKb2u/BQtjPDIvyk=
|
||||
github.com/jaytaylor/html2text v0.0.0-20200412013138-3577fbdbcff7 h1:g0fAGBisHaEQ0TRq1iBvemFRf+8AEWEmBESSiWB3Vsc=
|
||||
github.com/jaytaylor/html2text v0.0.0-20200412013138-3577fbdbcff7/go.mod h1:CVKlgaMiht+LXvHG173ujK6JUhZXKb2u/BQtjPDIvyk=
|
||||
github.com/levigross/exp-html v0.0.0-20120902181939-8df60c69a8f5 h1:W7p+m/AECTL3s/YR5RpQ4hz5SjNeKzZBl1q36ws12s0=
|
||||
github.com/levigross/exp-html v0.0.0-20120902181939-8df60c69a8f5/go.mod h1:QMe2wuKJ0o7zIVE8AqiT8rd8epmm6WDIZ2wyuBqYPzM=
|
||||
github.com/mattn/go-runewidth v0.0.3 h1:a+kO+98RDGEfo6asOGMmpodZq4FNtnGP54yps8BzLR4=
|
||||
github.com/mattn/go-runewidth v0.0.3/go.mod h1:LwmH8dsx7+W8Uxz3IHJYH5QSwggIsqBzpuz5H//U1FU=
|
||||
github.com/mattn/go-runewidth v0.0.7/go.mod h1:H031xJmbD/WCDINGzjvQ9THkh0rPKHF+m2gUSrubnMI=
|
||||
github.com/mattn/go-runewidth v0.0.9 h1:Lm995f3rfxdpd6TSmuVCHVb/QhupuXlYr8sCI/QdE+0=
|
||||
github.com/mattn/go-runewidth v0.0.9/go.mod h1:H031xJmbD/WCDINGzjvQ9THkh0rPKHF+m2gUSrubnMI=
|
||||
github.com/olekukonko/tablewriter v0.0.0-20180506121414-d4647c9c7a84 h1:fiKJgB4JDUd43CApkmCeTSQlWjtTtABrU2qsgbuP0BI=
|
||||
github.com/olekukonko/tablewriter v0.0.0-20180506121414-d4647c9c7a84/go.mod h1:vsDQFd/mU46D+Z4whnwzcISnGGzXWMclvtLoiIKAKIo=
|
||||
github.com/olekukonko/tablewriter v0.0.4 h1:vHD/YYe1Wolo78koG299f7V/VAS08c6IpCLn+Ejf/w8=
|
||||
github.com/olekukonko/tablewriter v0.0.4/go.mod h1:zq6QwlOf5SlnkVbMSr5EoBv3636FWnp+qbPhuoO21uA=
|
||||
@@ -57,7 +50,6 @@ github.com/otiai10/gosseract/v2 v2.2.4 h1:h/PV+oJqke8q2Ccw9bjpMBWfd7N2vtGDCUcihZ
|
||||
github.com/otiai10/gosseract/v2 v2.2.4/go.mod h1:ahOp/kHojnOMGv1RaUnR0jwY5JVa6BYKhYAS8nbMLSo=
|
||||
github.com/otiai10/mint v1.3.0 h1:Ady6MKVezQwHBkGzLFbrsywyp09Ah7rkmfjV3Bcr5uc=
|
||||
github.com/otiai10/mint v1.3.0/go.mod h1:F5AjcsTsWUqX+Na9fpHb52P8pcRX2CI6A3ctIT91xUo=
|
||||
github.com/pkg/errors v0.8.1 h1:iURUrRGxPUNPdy5/HRSm+Yj6okJ6UtLINN0Q9M4+h3I=
|
||||
github.com/pkg/errors v0.8.1/go.mod h1:bwawxfHBFNV+L2hUp1rHADufV3IMtnDRdf1r5NINEl0=
|
||||
github.com/pkg/errors v0.9.1 h1:FEBLx1zS214owpjy7qsBeixbURkuhQAwrK5UwLGTwt4=
|
||||
github.com/pkg/errors v0.9.1/go.mod h1:bwawxfHBFNV+L2hUp1rHADufV3IMtnDRdf1r5NINEl0=
|
||||
@@ -78,7 +70,6 @@ golang.org/x/net v0.0.0-20200602114024-627f9648deb9 h1:pNX+40auqi2JqRfOP1akLGtYc
|
||||
golang.org/x/net v0.0.0-20200602114024-627f9648deb9/go.mod h1:qpuaurCH72eLCgpAm/N6yyVIVM9cpaDIP3A8BGJEC5A=
|
||||
golang.org/x/sys v0.0.0-20190215142949-d0b11bdaac8a/go.mod h1:STP8DvDyc/dI5b8T5hshtkjS+E42TnysNCUPdjciGhY=
|
||||
golang.org/x/sys v0.0.0-20200323222414-85ca7c5b95cd/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
|
||||
golang.org/x/text v0.3.0 h1:g61tztE5qeGQ89tm6NTjjM9VPIm088od1l6aSorWRWg=
|
||||
golang.org/x/text v0.3.0/go.mod h1:NqM8EUOU14njkJ3fqMW+pc6Ldnwhi/IjpwHt7yyuwOQ=
|
||||
golang.org/x/text v0.3.2 h1:tW2bmiBqwgJj/UpqtC8EpXEZVYOwU0yG4iWbprSVAcs=
|
||||
golang.org/x/text v0.3.2/go.mod h1:bEr9sfX3Q8Zfm5fL9x+3itogRgK3+ptLWKqgva+5dAk=
|
||||
|
||||
2
vendor/code.sajari.com/docconv/local.go
сгенерированный
поставляемый
2
vendor/code.sajari.com/docconv/local.go
сгенерированный
поставляемый
@@ -25,7 +25,7 @@ func NewLocalFile(r io.Reader) (*LocalFile, error) {
|
||||
}, nil
|
||||
}
|
||||
|
||||
f, err := ioutil.TempFile(os.TempDir(), "/docconv")
|
||||
f, err := ioutil.TempFile(os.TempDir(), "docconv")
|
||||
if err != nil {
|
||||
return nil, fmt.Errorf("error creating temporary file: %v", err)
|
||||
}
|
||||
|
||||
15
vendor/code.sajari.com/docconv/pages.go
сгенерированный
поставляемый
15
vendor/code.sajari.com/docconv/pages.go
сгенерированный
поставляемый
@@ -12,7 +12,7 @@ import (
|
||||
|
||||
"github.com/golang/protobuf/proto"
|
||||
|
||||
"code.sajari.com/docconv/iWork"
|
||||
TSP "code.sajari.com/docconv/iWork"
|
||||
"code.sajari.com/docconv/snappy"
|
||||
)
|
||||
|
||||
@@ -48,8 +48,17 @@ func ConvertPages(r io.Reader) (string, map[string]string, error) {
|
||||
rc, _ := f.Open()
|
||||
defer rc.Close()
|
||||
bReader := bufio.NewReader(snappy.NewReader(io.MultiReader(strings.NewReader("\xff\x06\x00\x00sNaPpY"), rc)))
|
||||
archiveLength, err := binary.ReadVarint(bReader)
|
||||
archiveInfoData, err := ioutil.ReadAll(io.LimitReader(bReader, archiveLength))
|
||||
|
||||
// Ignore error.
|
||||
// NOTE: This error was unchecked. Need to revisit this to see if it
|
||||
// should be acted on.
|
||||
archiveLength, _ := binary.ReadVarint(bReader)
|
||||
|
||||
// Ignore error.
|
||||
// NOTE: This error was unchecked. Need to revisit this to see if it
|
||||
// should be acted on.
|
||||
archiveInfoData, _ := ioutil.ReadAll(io.LimitReader(bReader, archiveLength))
|
||||
|
||||
archiveInfo := &TSP.ArchiveInfo{}
|
||||
err = proto.Unmarshal(archiveInfoData, archiveInfo)
|
||||
fmt.Println("archiveInfo:", archiveInfo, err)
|
||||
|
||||
2
vendor/code.sajari.com/docconv/rtf.go
сгенерированный
поставляемый
2
vendor/code.sajari.com/docconv/rtf.go
сгенерированный
поставляемый
@@ -28,7 +28,7 @@ func ConvertRTF(r io.Reader) (string, map[string]string, error) {
|
||||
if parts := strings.SplitN(line, ":", 2); len(parts) > 1 {
|
||||
meta[strings.TrimSpace(parts[0])] = strings.TrimSpace(parts[1])
|
||||
}
|
||||
if len(line) > 4 && line[:4] != "### " {
|
||||
if !strings.HasPrefix(line, "### ") {
|
||||
output += line + "\n"
|
||||
}
|
||||
}
|
||||
|
||||
2
vendor/code.sajari.com/docconv/tidy.go
сгенерированный
поставляемый
2
vendor/code.sajari.com/docconv/tidy.go
сгенерированный
поставляемый
@@ -11,7 +11,7 @@ import (
|
||||
// Errors & warnings are deliberately suppressed as underlying tools
|
||||
// throw warnings very easily.
|
||||
func Tidy(r io.Reader, xmlIn bool) ([]byte, error) {
|
||||
f, err := ioutil.TempFile(os.TempDir(), "/docconv")
|
||||
f, err := ioutil.TempFile(os.TempDir(), "docconv")
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
|
||||
2
vendor/modules.txt
поставляемый
2
vendor/modules.txt
поставляемый
@@ -1,4 +1,4 @@
|
||||
# code.sajari.com/docconv v1.1.1-0.20200701232649-d9ea05fbd50a
|
||||
# code.sajari.com/docconv v1.1.1-0.20210427001343-7b3472bc323a
|
||||
## explicit
|
||||
code.sajari.com/docconv
|
||||
code.sajari.com/docconv/iWork
|
||||
|
||||
Ссылка в новой задаче
Block a user