-
Notifications
You must be signed in to change notification settings - Fork 2.4k
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
[pkg/ottl] Add ParseSimplifiedXML Converter (#35421)
This adds a converter called `ParseSimplifiedXML`. This serves as the final step described in #35281, which will allow users to parse any arbitrary XML document into user-friendly result, by first transforming the document in place with other functions (e.g. #35328 and #35364) and then calling this function. --------- Co-authored-by: Evan Bradley <[email protected]>
- Loading branch information
1 parent
41f6b0a
commit d4e17be
Showing
6 changed files
with
576 additions
and
0 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,27 @@ | ||
| # Use this changelog template to create an entry for release notes. | ||
|
|
||
| # One of 'breaking', 'deprecation', 'new_component', 'enhancement', 'bug_fix' | ||
| change_type: enhancement | ||
|
|
||
| # The name of the component, or a single word describing the area of concern, (e.g. filelogreceiver) | ||
| component: pkg/ottl | ||
|
|
||
| # A brief description of the change. Surround your text with quotes ("") if it needs to start with a backtick (`). | ||
| note: Add ParseSimplifiedXML Converter | ||
|
|
||
| # Mandatory: One or more tracking issues related to the change. You can use the PR number here if no issue exists. | ||
| issues: [35421] | ||
|
|
||
| # (Optional) One or more lines of additional information to render under the primary note. | ||
| # These lines will be padded with 2 spaces and then inserted directly into the document. | ||
| # Use pipe (|) for multiline entries. | ||
| subtext: | ||
|
|
||
| # If your change doesn't affect end users or the exported elements of any package, | ||
| # you should instead start your pull request title with [chore] or use the "Skip Changelog" label. | ||
| # Optional: The change log or logs in which this entry should be included. | ||
| # e.g. '[user]' or '[user, api]' | ||
| # Include 'user' if the change is relevant to end users. | ||
| # Include 'api' if there is a change to a library API. | ||
| # Default: '[user]' | ||
| change_logs: [] |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,134 @@ | ||
| // Copyright The OpenTelemetry Authors | ||
| // SPDX-License-Identifier: Apache-2.0 | ||
|
|
||
| package ottlfuncs // import "github.com/open-telemetry/opentelemetry-collector-contrib/pkg/ottl/ottlfuncs" | ||
|
|
||
| import ( | ||
| "context" | ||
| "fmt" | ||
|
|
||
| "github.com/antchfx/xmlquery" | ||
| "go.opentelemetry.io/collector/pdata/pcommon" | ||
|
|
||
| "github.com/open-telemetry/opentelemetry-collector-contrib/pkg/ottl" | ||
| ) | ||
|
|
||
| type ParseSimplifiedXMLArguments[K any] struct { | ||
| Target ottl.StringGetter[K] | ||
| } | ||
|
|
||
| func NewParseSimplifiedXMLFactory[K any]() ottl.Factory[K] { | ||
| return ottl.NewFactory("ParseSimplifiedXML", &ParseSimplifiedXMLArguments[K]{}, createParseSimplifiedXMLFunction[K]) | ||
| } | ||
|
|
||
| func createParseSimplifiedXMLFunction[K any](_ ottl.FunctionContext, oArgs ottl.Arguments) (ottl.ExprFunc[K], error) { | ||
| args, ok := oArgs.(*ParseSimplifiedXMLArguments[K]) | ||
|
|
||
| if !ok { | ||
| return nil, fmt.Errorf("ParseSimplifiedXML args must be of type *ParseSimplifiedXMLAguments[K]") | ||
| } | ||
|
|
||
| return parseSimplifiedXML(args.Target), nil | ||
| } | ||
|
|
||
| // The `ParseSimplifiedXML` Converter returns a `pcommon.Map` struct that is the result of parsing the target | ||
| // string without preservation of attributes or extraneous text content. | ||
| func parseSimplifiedXML[K any](target ottl.StringGetter[K]) ottl.ExprFunc[K] { | ||
| return func(ctx context.Context, tCtx K) (any, error) { | ||
| var doc *xmlquery.Node | ||
| if targetVal, err := target.Get(ctx, tCtx); err != nil { | ||
| return nil, err | ||
| } else if doc, err = parseNodesXML(targetVal); err != nil { | ||
| return nil, err | ||
| } | ||
|
|
||
| docMap := pcommon.NewMap() | ||
| parseElement(doc, &docMap) | ||
| return docMap, nil | ||
| } | ||
| } | ||
|
|
||
| func parseElement(parent *xmlquery.Node, parentMap *pcommon.Map) { | ||
| // Count the number of each element tag so we know whether it will be a member of a slice or not | ||
| childTags := make(map[string]int) | ||
| for child := parent.FirstChild; child != nil; child = child.NextSibling { | ||
| if child.Type != xmlquery.ElementNode { | ||
| continue | ||
| } | ||
| childTags[child.Data]++ | ||
| } | ||
| if len(childTags) == 0 { | ||
| return | ||
| } | ||
|
|
||
| // Convert the children, now knowing whether they will be a member of a slice or not | ||
| for child := parent.FirstChild; child != nil; child = child.NextSibling { | ||
| if child.Type != xmlquery.ElementNode || child.FirstChild == nil { | ||
| continue | ||
| } | ||
|
|
||
| leafValue := leafValueFromElement(child) | ||
|
|
||
| // Slice of the same element | ||
| if childTags[child.Data] > 1 { | ||
| // Get or create the slice of children | ||
| var childrenSlice pcommon.Slice | ||
| childrenValue, ok := parentMap.Get(child.Data) | ||
| if ok { | ||
| childrenSlice = childrenValue.Slice() | ||
| } else { | ||
| childrenSlice = parentMap.PutEmptySlice(child.Data) | ||
| } | ||
|
|
||
| // Add the child's text content to the slice | ||
| if leafValue != "" { | ||
| childrenSlice.AppendEmpty().SetStr(leafValue) | ||
| continue | ||
| } | ||
|
|
||
| // Parse the child to make sure there's something to add | ||
| childMap := pcommon.NewMap() | ||
| parseElement(child, &childMap) | ||
| if childMap.Len() == 0 { | ||
| continue | ||
| } | ||
|
|
||
| sliceValue := childrenSlice.AppendEmpty() | ||
| sliceMap := sliceValue.SetEmptyMap() | ||
| childMap.CopyTo(sliceMap) | ||
| continue | ||
| } | ||
|
|
||
| if leafValue != "" { | ||
| parentMap.PutStr(child.Data, leafValue) | ||
| continue | ||
| } | ||
|
|
||
| // Child will be a map | ||
| childMap := pcommon.NewMap() | ||
| parseElement(child, &childMap) | ||
| if childMap.Len() == 0 { | ||
| continue | ||
| } | ||
|
|
||
| childMap.CopyTo(parentMap.PutEmptyMap(child.Data)) | ||
| } | ||
| } | ||
|
|
||
| func leafValueFromElement(node *xmlquery.Node) string { | ||
| // First check if there are any child elements. If there are, ignore any extraneous text. | ||
| for child := node.FirstChild; child != nil; child = child.NextSibling { | ||
| if child.Type == xmlquery.ElementNode { | ||
| return "" | ||
| } | ||
| } | ||
|
|
||
| // No child elements, so return the first text or CDATA content | ||
| for child := node.FirstChild; child != nil; child = child.NextSibling { | ||
| switch child.Type { | ||
| case xmlquery.TextNode, xmlquery.CharDataNode: | ||
| return child.Data | ||
| } | ||
| } | ||
| return "" | ||
| } |
Oops, something went wrong.