Thanks to visit codestin.com
Credit goes to github.com

Skip to content

fix: enable select current element for struct slice unmarshal #748

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 3 commits into
base: master
Choose a base branch
from
Open

fix: enable select current element for struct slice unmarshal #748

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
5e3e5e7
fix: enable select current element for string selector
xzvwang Jan 12, 2023
580970a
Merge branch 'master' into master
xzvwang Jan 16, 2023
7336492
Merge branch 'gocolly:master' into master
xzvwang Apr 18, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
25 changes: 18 additions & 7 deletions unmarshal.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -96,8 +96,7 @@ func unmarshalSelector(s *goquery.Selection, attrV reflect.Value, selector strin
return err
}
case reflect.String:
val := getDOMValue(s.Find(selector), htmlAttr)
attrV.Set(reflect.Indirect(reflect.ValueOf(val)))
unmarshalString(s, selector, htmlAttr, attrV)
case reflect.Struct:
if err := unmarshalStruct(s, selector, attrV); err != nil {
return err
Expand Down Expand Up @@ -126,8 +125,7 @@ func unmarshalAttr(s *goquery.Selection, attrV reflect.Value, attrT reflect.Stru
return err
}
case reflect.String:
val := getDOMValue(s.Find(selector), htmlAttr)
attrV.Set(reflect.Indirect(reflect.ValueOf(val)))
unmarshalString(s, selector, htmlAttr, attrV)
case reflect.Struct:
if err := unmarshalStruct(s, selector, attrV); err != nil {
return err
Expand All @@ -142,6 +140,15 @@ func unmarshalAttr(s *goquery.Selection, attrV reflect.Value, attrT reflect.Stru
return nil
}

func unmarshalString(s *goquery.Selection, selector string, htmlAttr string, attrV reflect.Value) {
newS := s
if selector != "" {
newS = newS.Find(selector)
}
val := getDOMValue(newS, htmlAttr)
attrV.Set(reflect.Indirect(reflect.ValueOf(val)))
}

func unmarshalStruct(s *goquery.Selection, selector string, attrV reflect.Value) error {
newS := s
if selector != "" {
Expand Down Expand Up @@ -185,20 +192,24 @@ func unmarshalSlice(s *goquery.Selection, selector, htmlAttr string, attrV refle
v := reflect.MakeSlice(attrV.Type(), 0, 0)
attrV.Set(v)
}
newS := s
if selector != "" {
newS = newS.Find(selector)
}
switch attrV.Type().Elem().Kind() {
case reflect.String:
s.Find(selector).Each(func(_ int, s *goquery.Selection) {
newS.Each(func(_ int, s *goquery.Selection) {
val := getDOMValue(s, htmlAttr)
attrV.Set(reflect.Append(attrV, reflect.Indirect(reflect.ValueOf(val))))
})
case reflect.Ptr:
s.Find(selector).Each(func(_ int, innerSel *goquery.Selection) {
newS.Each(func(_ int, innerSel *goquery.Selection) {
someVal := reflect.New(attrV.Type().Elem().Elem())
UnmarshalHTML(someVal.Interface(), innerSel, nil)
attrV.Set(reflect.Append(attrV, someVal))
})
case reflect.Struct:
s.Find(selector).Each(func(_ int, innerSel *goquery.Selection) {
newS.Each(func(_ int, innerSel *goquery.Selection) {
someVal := reflect.New(attrV.Type().Elem())
UnmarshalHTML(someVal.Interface(), innerSel, nil)
attrV.Set(reflect.Append(attrV, reflect.Indirect(someVal)))
Expand Down
19 changes: 17 additions & 2 deletions unmarshal_test.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -23,7 +23,7 @@ import (

var basicTestData = []byte(`<ul><li class="x">list <span>item</span> 1</li><li>list item 2</li><li>3</li></ul>`)
var nestedTestData = []byte(`<div><p>a</p><div><p>b</p><div><p>c</p></div></div></div>`)
var pointerSliceTestData = []byte(`<ul class="object"><li class="info">Information: <span>Info 1</span></li><li class="info">Information: <span>Info 2</span></li></ul>`)
var pointerSliceTestData = []byte(`<ul class="object"><li class="info">Information: <span>Info 1</span></li><li class="info">Information: <span>Info 2</span></li> <a href="url1">Name 1</a><a href="url2">Name 2</a></ul>`)

func TestBasicUnmarshal(t *testing.T) {
doc, _ := goquery.NewDocumentFromReader(bytes.NewBuffer(basicTestData))
Expand Down Expand Up @@ -138,8 +138,14 @@ func TestStructSliceUnmarshall(t *testing.T) {
type info struct {
Text string `selector:"span"`
}
type urlWithName struct {
Name string `selector:""`
URL string `selector:"" attr:"href"`
}

type object struct {
Info []info `selector:"li.info"`
Info []info `selector:"li.info"`
Urls []*urlWithName `selector:"a"`
}

doc, _ := goquery.NewDocumentFromReader(bytes.NewBuffer(pointerSliceTestData))
Expand All @@ -160,4 +166,13 @@ func TestStructSliceUnmarshall(t *testing.T) {
t.Errorf("Invalid data for Info.[1].Text: %s, expected Info 2", o.Info[1].Text)
}

if len(o.Urls) != 2 {
t.Errorf("Invalid length for Urls: %d, expected 2", len(o.Info))
}
if o.Urls[0].Name != "Name 1" || o.Urls[0].URL != "url1" {
t.Errorf("Invalid data for Urls.[0].Name: %s or Urls.[0].URL: %s, expected Name 1 and url1", o.Urls[0].Name, o.Urls[0].URL)
}
if o.Urls[1].Name != "Name 2" || o.Urls[1].URL != "url2" {
t.Errorf("Invalid data for Urls.[1].Name: %s or Urls.[1].URL: %s, expected Name 2 and url2", o.Urls[1].Name, o.Urls[1].URL)
}
}