fix XML parsing (#2)

- Use antchfx/xmlquery for easier XML parsing. No more regexp wrangling and the result is much more reliable over a variety of ebooks. Much good.
- fix chapter selection, look for `<?xml[...]` which is much more reliable
- add option `-x` to dump the XML ebook source for debugging
This commit is contained in:
T.v.Dein
2025-10-16 18:57:05 +02:00
committed by GitHub
parent 90d30cb3e1
commit b50c6acff0
13 changed files with 143 additions and 71 deletions

Binary file not shown.

Before

Width:  |  Height:  |  Size: 57 KiB

After

Width:  |  Height:  |  Size: 35 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 79 KiB

After

Width:  |  Height:  |  Size: 40 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 74 KiB

After

Width:  |  Height:  |  Size: 37 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 55 KiB

After

Width:  |  Height:  |  Size: 32 KiB

View File

@@ -16,7 +16,7 @@ import (
)
const (
Version string = `v0.0.2`
Version string = `v0.0.3`
Usage string = `Usage epuppy [options] <epub file>
Options:
@@ -25,6 +25,7 @@ Options:
-n --line-numbers add line numbers
-c --config <file> use config <file>
-t --txt dump readable content to STDOUT
-x --xml dump source xml to STDOUT
-d --debug enable debugging
-h --help show help message
-v --version show program version`
@@ -37,6 +38,7 @@ type Config struct {
Darkmode bool `koanf:"dark"` // -D
LineNumbers bool `koanf:"line-numbers"` // -n
Dump bool `koanf:"txt"` // -t
XML bool `koanf:"xml"` // -x
Config string `koanf:"config"` // -c
ColorDark ColorSetting `koanf:"colordark"` // comes from config file only
ColorLight ColorSetting `koanf:"colorlight"` // comes from config file only
@@ -66,6 +68,7 @@ func InitConfig(output io.Writer) (*Config, error) {
flagset.BoolP("store-progress", "s", false, "store reading progress")
flagset.BoolP("line-numbers", "n", false, "add line numbers")
flagset.BoolP("txt", "t", false, "dump readable content to STDOUT")
flagset.BoolP("xml", "x", false, "dump xml to STDOUT")
flagset.StringP("config", "c", "", "read config from file")
if err := flagset.Parse(os.Args[1:]); err != nil {

View File

@@ -2,7 +2,6 @@ package cmd
import (
"fmt"
"log"
"os"
"path/filepath"
"strings"
@@ -33,17 +32,11 @@ func ViewText(conf *Config) (int, error) {
}
func ViewEpub(conf *Config) (int, error) {
book, err := epub.Open(conf.Document)
book, err := epub.Open(conf.Document, conf.XML)
if err != nil {
return 0, err
}
defer func() {
if err := book.Close(); err != nil {
log.Fatal(err)
}
}()
buf := strings.Builder{}
head := strings.Builder{}
@@ -59,9 +52,20 @@ func ViewEpub(conf *Config) (int, error) {
head.WriteString(" ")
}
// FIXME: since the switch to book.Files() in epub.Open() this
// returns invalid chapter numbering
fetchByContent(conf, &buf, book)
if conf.Dump {
return fmt.Println(buf.String())
}
return Pager(conf, head.String(), buf.String())
}
// FIXME: since the switch to book.Files() in epub.Open() this
// returns invalid chapter numbering
func fetchByContent(conf *Config, buf *strings.Builder, book *epub.Book) bool {
chapter := 1
var gotbody bool
for _, content := range book.Content {
if len(content.Body) > 0 {
@@ -81,13 +85,10 @@ func ViewEpub(conf *Config) (int, error) {
buf.WriteString("\r\n\r\n\r\n\r\n")
chapter++
gotbody = true
}
}
if conf.Dump {
return fmt.Println(buf.String())
}
return Pager(conf, head.String(), buf.String())
return gotbody
}

6
go.mod
View File

@@ -6,6 +6,7 @@ toolchain go1.24.9
require (
github.com/alecthomas/repr v0.5.2
github.com/antchfx/xmlquery v1.5.0
github.com/knadh/koanf/parsers/toml v0.1.0
github.com/knadh/koanf/providers/file v1.2.0
github.com/knadh/koanf/providers/posflag v1.0.1
@@ -35,14 +36,17 @@ require (
github.com/rivo/uniseg v0.4.7 // indirect
github.com/xo/terminfo v0.0.0-20220910002029-abceb7e1c41e // indirect
golang.org/x/sys v0.37.0 // indirect
golang.org/x/text v0.3.8 // indirect
golang.org/x/text v0.30.0 // indirect
)
require (
github.com/antchfx/xpath v1.3.5 // indirect
github.com/fsnotify/fsnotify v1.9.0 // indirect
github.com/go-viper/mapstructure/v2 v2.4.0 // indirect
github.com/golang/groupcache v0.0.0-20210331224755-41bb18bfe9da // indirect
github.com/knadh/koanf/maps v0.1.2 // indirect
github.com/mitchellh/copystructure v1.2.0 // indirect
github.com/mitchellh/reflectwalk v1.0.2 // indirect
github.com/pelletier/go-toml v1.9.5 // indirect
golang.org/x/net v0.33.0 // indirect
)

76
go.sum
View File

@@ -1,5 +1,9 @@
github.com/alecthomas/repr v0.5.2 h1:SU73FTI9D1P5UNtvseffFSGmdNci/O6RsqzeXJtP0Qs=
github.com/alecthomas/repr v0.5.2/go.mod h1:Fr0507jx4eOXV7AlPV6AVZLYrLIuIeSOWtW57eE/O/4=
github.com/antchfx/xmlquery v1.5.0 h1:uAi+mO40ZWfyU6mlUBxRVvL6uBNZ6LMU4M3+mQIBV4c=
github.com/antchfx/xmlquery v1.5.0/go.mod h1:lJfWRXzYMK1ss32zm1GQV3gMIW/HFey3xDZmkP1SuNc=
github.com/antchfx/xpath v1.3.5 h1:PqbXLC3TkfeZyakF5eeh3NTWEbYl4VHNVeufANzDbKQ=
github.com/antchfx/xpath v1.3.5/go.mod h1:i54GszH55fYfBmoZXapTHN8T8tkcHfRgLyVwwqzXNcs=
github.com/aymanbagabas/go-osc52/v2 v2.0.1 h1:HwpRHbFMcZLEVr42D4p7XBqjyuxQH5SMiErDT4WkJ2k=
github.com/aymanbagabas/go-osc52/v2 v2.0.1/go.mod h1:uYgXzlJ7ZpABp8OJ+exZzJJhRNQ2ASbcXHWsFqH8hp8=
github.com/aymanbagabas/go-udiff v0.2.0 h1:TK0fH4MteXUDspT88n8CKzvK0X9O2xu9yQjWpi6yML8=
@@ -28,6 +32,9 @@ github.com/fsnotify/fsnotify v1.9.0 h1:2Ml+OJNzbYCTzsxtv8vKSFD9PbJjmhYF14k/jKC7S
github.com/fsnotify/fsnotify v1.9.0/go.mod h1:8jBTzvmWwFyi3Pb8djgCCO5IBqzKJ/Jwo8TRcHyHii0=
github.com/go-viper/mapstructure/v2 v2.4.0 h1:EBsztssimR/CONLSZZ04E8qAkxNYq4Qp9LvH92wZUgs=
github.com/go-viper/mapstructure/v2 v2.4.0/go.mod h1:oJDH3BJKyqBA2TXFhDsKDGDTlndYOZ6rGS0BRZIxGhM=
github.com/golang/groupcache v0.0.0-20210331224755-41bb18bfe9da h1:oI5xCqsCo564l8iNU+DwB5epxmsaqB+rhGL0m5jtYqE=
github.com/golang/groupcache v0.0.0-20210331224755-41bb18bfe9da/go.mod h1:cIg4eruTrX1D+g88fzRXU5OdNfaM+9IcxsU14FzY7Hc=
github.com/google/go-cmp v0.6.0/go.mod h1:17dUlkBOakJ0+DkrSSNjCkIjxS6bF9zb3elmeNGIjoY=
github.com/knadh/koanf/maps v0.1.2 h1:RBfmAW5CnZT+PJ1CVc1QSJKf4Xu9kxfQgYVQSu8hpbo=
github.com/knadh/koanf/maps v0.1.2/go.mod h1:npD/QZY3V6ghQDdcQzl1W4ICNVTkohC8E73eI2xW4yI=
github.com/knadh/koanf/parsers/toml v0.1.0 h1:S2hLqS4TgWZYj4/7mI5m1CQQcWurxUz6ODgOub/6LCI=
@@ -73,15 +80,80 @@ github.com/stretchr/testify v1.8.1 h1:w7B6lhMri9wdJUVmEZPGGhZzrYTPvgJArz7wNPgYKs
github.com/stretchr/testify v1.8.1/go.mod h1:w2LPCIKwWwSfY2zedu0+kehJoqGctiVI29o6fzry7u4=
github.com/xo/terminfo v0.0.0-20220910002029-abceb7e1c41e h1:JVG44RsyaB9T2KIHavMF/ppJZNG9ZpyihvCd0w101no=
github.com/xo/terminfo v0.0.0-20220910002029-abceb7e1c41e/go.mod h1:RbqR21r5mrJuqunuUZ/Dhy/avygyECGrLceyNeo4LiM=
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/crypto v0.13.0/go.mod h1:y6Z2r+Rw4iayiXXAIxJIDAJ1zMW4yaTpebo8fPOliYc=
golang.org/x/crypto v0.19.0/go.mod h1:Iy9bg/ha4yyC70EfRS8jz+B6ybOBKMaSxLj6P6oBDfU=
golang.org/x/crypto v0.23.0/go.mod h1:CKFgDieR+mRhux2Lsu27y0fO304Db0wZe70UKqHu0v8=
golang.org/x/crypto v0.31.0/go.mod h1:kDsLvtWBEx7MV9tJOj9bnXsPbxwJQ6csT/x4KIN4Ssk=
golang.org/x/exp v0.0.0-20220909182711-5c715a9e8561 h1:MDc5xs78ZrZr3HMQugiXOAkSZtfTpbJLDr/lwfgO53E=
golang.org/x/exp v0.0.0-20220909182711-5c715a9e8561/go.mod h1:cyybsKvd6eL0RnXn6p/Grxp8F5bW7iYuBgsNCOHpMYE=
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/mod v0.12.0/go.mod h1:iBbtSCu2XBx23ZKBPSOrRkjjQPZFPuis4dIYUhu/chs=
golang.org/x/mod v0.15.0/go.mod h1:hTbmBsO62+eylJbnUtE2MGJUyE7QWk4xUqPFrRgJ+7c=
golang.org/x/mod v0.17.0/go.mod h1:hTbmBsO62+eylJbnUtE2MGJUyE7QWk4xUqPFrRgJ+7c=
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/net v0.10.0/go.mod h1:0qNGK6F8kojg2nk9dLZ2mShWaEBan6FAoqfSigmmuDg=
golang.org/x/net v0.15.0/go.mod h1:idbUs1IY1+zTqbi8yxTbhexhEEk5ur9LInksu6HrEpk=
golang.org/x/net v0.21.0/go.mod h1:bIjVDfnllIU7BJ2DNgfnXvpSvtn8VRwhlsaeUTyUS44=
golang.org/x/net v0.25.0/go.mod h1:JkAGAh7GEvH74S6FOH42FLoXpXbE/aqXSrIQjXgsiwM=
golang.org/x/net v0.33.0 h1:74SYHlV8BIgHIFC/LrYkOGIwL19eTYXQ5wc6TBuO36I=
golang.org/x/net v0.33.0/go.mod h1:HXLR5J+9DxmrqMwG9qjGCxZ+zKXxBru04zlTvWlWuN4=
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/sync v0.3.0/go.mod h1:FU7BRWz2tNW+3quACPkgCx/L+uEAv1htQ0V83Z9Rj+Y=
golang.org/x/sync v0.6.0/go.mod h1:Czt+wKu1gCyEFDUtn0jG5QVvpJ6rzVqr5aXyt9drQfk=
golang.org/x/sync v0.7.0/go.mod h1:Czt+wKu1gCyEFDUtn0jG5QVvpJ6rzVqr5aXyt9drQfk=
golang.org/x/sync v0.10.0/go.mod h1:Czt+wKu1gCyEFDUtn0jG5QVvpJ6rzVqr5aXyt9drQfk=
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 v0.0.0-20210809222454-d867a43fc93e/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
golang.org/x/sys v0.0.0-20220520151302-bc2c85ada10a/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
golang.org/x/sys v0.0.0-20220722155257-8c9f86f7a55f/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
golang.org/x/sys v0.5.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
golang.org/x/sys v0.6.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
golang.org/x/sys v0.8.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
golang.org/x/sys v0.12.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
golang.org/x/sys v0.17.0/go.mod h1:/VUhepiaJMQUp4+oa/7Zr1D23ma6VTLIYjOOTFZPUcA=
golang.org/x/sys v0.20.0/go.mod h1:/VUhepiaJMQUp4+oa/7Zr1D23ma6VTLIYjOOTFZPUcA=
golang.org/x/sys v0.28.0/go.mod h1:/VUhepiaJMQUp4+oa/7Zr1D23ma6VTLIYjOOTFZPUcA=
golang.org/x/sys v0.37.0 h1:fdNQudmxPjkdUTPnLn5mdQv7Zwvbvpaxqs831goi9kQ=
golang.org/x/sys v0.37.0/go.mod h1:OgkHotnGiDImocRcuBABYBEXf8A9a87e/uXjp9XT3ks=
golang.org/x/telemetry v0.0.0-20240228155512-f48c80bd79b2/go.mod h1:TeRTkGYfJXctD9OcfyVLyj2J3IxLnKwHJR8f4D8a3YE=
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/term v0.8.0/go.mod h1:xPskH00ivmX89bAKVGSKKtLOWNx2+17Eiy94tnKShWo=
golang.org/x/term v0.12.0/go.mod h1:owVbMEjm3cBLCHdkQu9b1opXd4ETQWc3BhuQGKgXgvU=
golang.org/x/term v0.17.0/go.mod h1:lLRBjIVuehSbZlaOtGMbcMncT+aqLLLmKrsjNrUguwk=
golang.org/x/term v0.20.0/go.mod h1:8UkIAJTvZgivsXaD6/pH6U9ecQzZ45awqEOzuCvwpFY=
golang.org/x/term v0.27.0/go.mod h1:iMsnZpn0cago0GOrHO2+Y7u7JPn5AylBrcoWkElMTSM=
golang.org/x/term v0.36.0 h1:zMPR+aF8gfksFprF/Nc/rd1wRS1EI6nDBGyWAvDzx2Q=
golang.org/x/term v0.36.0/go.mod h1:Qu394IJq6V6dCBRgwqshf3mPF85AqzYEzofzRdZkWss=
golang.org/x/text v0.3.8 h1:nAL+RVCQ9uMn3vJZbV+MRnydTJFPf8qqY42YiA6MrqY=
golang.org/x/text v0.3.8/go.mod h1:E6s5w1FMmriuDzIBO73fBruAKo1PCIq6d2Q6DHfQ8WQ=
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 v0.9.0/go.mod h1:e1OnstbJyHTd6l/uOt8jFFHp6TRDWZR/bV3emEE/zU8=
golang.org/x/text v0.13.0/go.mod h1:TvPlkZtksWOMsz7fbANvkp4WM8x/WCo/om8BMLbz+aE=
golang.org/x/text v0.14.0/go.mod h1:18ZOQIKpY8NJVqYksKHtTdi31H5itFRjB5/qKTNYzSU=
golang.org/x/text v0.15.0/go.mod h1:18ZOQIKpY8NJVqYksKHtTdi31H5itFRjB5/qKTNYzSU=
golang.org/x/text v0.21.0/go.mod h1:4IBbMaMmOPCJ8SecivzSH54+73PCFmPWxNTLm+vZkEQ=
golang.org/x/text v0.30.0 h1:yznKA/E9zq54KzlzBEAWn1NXSQ8DIp/NYMy88xJjl4k=
golang.org/x/text v0.30.0/go.mod h1:yDdHFIX9t+tORqspjENWgzaCVXgk0yYnYuSZ8UzzBVM=
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/tools v0.13.0/go.mod h1:HvlwmtVNQAhOuCjW7xxvovg8wbNq7LwfXh/k7wXUl58=
golang.org/x/tools v0.21.1-0.20240508182429-e35e4ccd0d2d/go.mod h1:aiJjzUbINMkxbQROHiO6hDPo2LHcIPhhQsa9DLh0yGk=
golang.org/x/xerrors v0.0.0-20190717185122-a985d3407aa7/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=
gopkg.in/yaml.v3 v3.0.1 h1:fxVm/GzAzEWqLHuvctI91KS9hhNmmWOoWu0XTYJS7CA=
gopkg.in/yaml.v3 v3.0.1/go.mod h1:K4uyk7z7BCEPqu6E+C64Yfv1cQ7kz7rIZviUmN+EgEM=

View File

@@ -16,8 +16,7 @@ type Book struct {
Container Container `json:"-"`
Mimetype string `json:"-"`
Content []Content
fd *zip.ReadCloser
fd *zip.ReadCloser
}
// Open open resource file
@@ -34,11 +33,6 @@ func (p *Book) Files() []string {
return fns
}
// Close close file reader
func (p *Book) Close() error {
return p.fd.Close()
}
// -----------------------------------------------------------------------------
func (p *Book) filename(n string) string {
return path.Join(path.Dir(p.Container.Rootfile.Path), n)

View File

@@ -1,19 +1,16 @@
package epub
import (
"encoding/xml"
"fmt"
"regexp"
"strings"
"github.com/antchfx/xmlquery"
)
var (
cleantitle = regexp.MustCompile(`(?s)<head>.*</head>`)
cleanmarkup = regexp.MustCompile(`<[^<>]+>`)
cleanentities = regexp.MustCompile(`&.+;`)
cleancomments = regexp.MustCompile(`/*.*/`)
cleanspace = regexp.MustCompile(`^\s*`)
cleanh1 = regexp.MustCompile(`<h[1-6].*</h[1-6]>`)
cleanentitles = regexp.MustCompile(`&.+;`)
empty = regexp.MustCompile(`(?s)^[\s ]*$`)
newlines = regexp.MustCompile(`[\r\n]+`)
)
// Content nav-point content
@@ -26,25 +23,30 @@ type Content struct {
}
func (c *Content) String(content []byte) error {
title := Title{}
err := xml.Unmarshal(content, &title)
// parse XML, look for title and <p>.*</p> stuff
doc, err := xmlquery.Parse(
strings.NewReader(
cleanentitles.ReplaceAllString(string(content), " ")))
if err != nil {
if !strings.HasPrefix(err.Error(), "XML syntax error") {
return fmt.Errorf("XML parser error %w", err)
panic(err)
}
// extract the title
for _, item := range xmlquery.Find(doc, "//title") {
c.Title = strings.TrimSpace(item.InnerText())
}
// extract all paragraphs, ignore any formatting and re-fill the
// paragraph, that is, we replaces all newlines inside with one
// space.
txt := strings.Builder{}
for _, item := range xmlquery.Find(doc, "//p") {
if !empty.MatchString(item.InnerText()) {
txt.WriteString(newlines.ReplaceAllString(item.InnerText(), " ") + "\n\n")
}
}
c.Title = strings.TrimSpace(title.Content)
txt := cleantitle.ReplaceAllString(string(content), "")
txt = cleanh1.ReplaceAllString(txt, "")
txt = cleanmarkup.ReplaceAllString(txt, "")
txt = cleanentities.ReplaceAllString(txt, " ")
txt = cleancomments.ReplaceAllString(txt, "")
txt = strings.TrimSpace(txt)
c.Body = cleanspace.ReplaceAllString(txt, "")
c.Body = strings.TrimSpace(txt.String())
c.XML = content
if len(c.Body) == 0 {

View File

@@ -1,36 +1,22 @@
package epub
import (
"log"
"testing"
)
func TestEpub(t *testing.T) {
bk, err := open(t, "test.epub")
_, err := open(t, "test.epub")
if err != nil {
t.Fatal(err)
}
defer func() {
if err := bk.Close(); err != nil {
log.Fatal(err)
}
}()
}
func open(t *testing.T, f string) (*Book, error) {
bk, err := Open(f)
bk, err := Open(f, false)
if err != nil {
return nil, err
}
defer func() {
if err := bk.Close(); err != nil {
log.Fatal(err)
}
}()
t.Logf("files: %+v", bk.Files())
t.Logf("book: %+v", bk)

View File

@@ -7,8 +7,9 @@ type Ncx struct {
// NavPoint nav point
type NavPoint struct {
Text string `xml:"navLabel>text" json:"text"`
Points []NavPoint `xml:"navPoint" json:"points"`
Text string `xml:"navLabel>text" json:"text"`
Content Content `xml:"content" json:"content"`
Points []NavPoint `xml:"navPoint" json:"points"`
}
type Title struct {

View File

@@ -2,12 +2,14 @@ package epub
import (
"archive/zip"
"fmt"
"log"
"os"
"strings"
)
// Open open a epub file
func Open(fn string) (*Book, error) {
func Open(fn string, dumpxml bool) (*Book, error) {
fd, err := zip.OpenReader(fn)
if err != nil {
return nil, err
@@ -55,14 +57,21 @@ func Open(fn string) (*Book, error) {
}
ct := Content{Src: file}
if strings.Contains(string(content), "DOCTYPE") {
if strings.Contains(string(content), "<?xml") {
if err := ct.String(content); err != nil {
return &bk, err
}
}
bk.Content = append(bk.Content, ct)
if dumpxml {
fmt.Println(string(ct.XML))
}
}
if dumpxml {
os.Exit(0)
}
return &bk, nil