Remove path parts from component label suffixes (#38622)

<!--Ex. Fixing a bug - Describe the bug and how this fixes the issue.
Ex. Adding a feature - Explain what this achieves.-->
#### Description
To generate labels for all components, including those with paths longer
than 50 characters:
In the root Makefile, a phony target is created to generate the
.github/component_labels file, which contains the component paths and
their corresponding labels (shortened paths for those exceeding 50
characters by removing repeated patterns in the string). The file is
space-delimited.
In the build-and-test workflow, under the checks job, a step is added to
verify that the .github/component_labels file exists.
The scripts used in the workflows are adjusted to use the
.github/component_labels file as a reference for mappings between
component paths and their labels.

<!-- Issue number (e.g. #1234) or full URL to issue, if applicable. -->
#### Link to tracking issue
Fixes #38527

Author: gabgg71

.chloggen/shorten-labels.yaml

@@ -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: workflow
+
+# A brief description of the change.  Surround your text with quotes ("") if it needs to start with a backtick (`).
+note: Remove path parts from component label suffixes 
+
+# Mandatory: One or more tracking issues related to the change. You can use the PR number here if no issue exists.
+issues: [38527]
+
+# (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: [user]

.github/component_labels.txt

@@ -220,6 +220,10 @@ jobs:
         run: |
           make gendistributions
           git diff -s --exit-code || (echo 'Generated code is out of date, please run "make gendistributions" and commit the changes in this PR.' && exit 1)
+      - name: Gen labels
+        run: |
+          make genlabels
+          git diff -s --exit-code || (echo '.github/component_labels.txt is out of date, please run "make genlabels" and commit the changes in this PR.' && exit 1)
       - name: CodeGen
         run: |
           make generate

.github/workflows/build-and-test.yml

@@ -90,18 +90,17 @@ main () {
                 REVIEWERS+=$(echo -n "${OWNER}" | sed -E 's/@(.+)/"\1"/')
             done
 
-            # Convert the CODEOWNERS entry to a label
-            COMPONENT_NAME=$(echo -n "${COMPONENT}" | sed -E 's%^(.+)/(.+)\1%\1/\2%')
+            LABEL_NAME="$(awk -v path="${COMPONENT}" '$1 == path {print $2}' .github/component_labels.txt)"
 
-            if (( "${#COMPONENT_NAME}" > 50 )); then
-                echo "'${COMPONENT_NAME}' exceeds GitHub's 50-character limit on labels, skipping adding label"
+            if (( "${#LABEL_NAME}" > 50 )); then
+                echo "'${LABEL_NAME}' exceeds GitHub's 50-character limit on labels, skipping adding label"
                 continue
             fi
 
             if [[ -n "${LABELS}" ]]; then
                 LABELS+=","
             fi
-            LABELS+="${COMPONENT_NAME}"
+            LABELS+="${LABEL_NAME}"
         done
     done
 

.github/workflows/scripts/add-codeowners-to-pr.sh

@@ -58,17 +58,15 @@ for LABEL_REQ in ${LABELS}; do
         continue
     fi
 
-    # Grep exits with status code 1 if there are no matches,
-    # so we manually set RESULT to 0 if nothing is found.
-    RESULT=$(grep -c "${LABEL}" .github/CODEOWNERS || true)
+    SHORT_LABEL=$(awk -v path="${LABEL}" '$1 == path || $2 == path {print $2}' .github/component_labels.txt)
 
-    if [[ ${RESULT} = 0 ]]; then
-        echo "\"${LABEL}\" doesn't correspond to a component, skipping."
+    if [[  -z "${SHORT_LABEL}" ]]; then
+        echo "\"${SHORT_LABEL}\" doesn't correspond to a component, skipping."
         continue
     fi
 
     if [[ ${SHOULD_ADD} = true ]]; then
-        gh issue edit "${ISSUE}" --add-label "${LABEL}"
+        gh issue edit "${ISSUE}" --add-label "${SHORT_LABEL}"
 
         # Labels added by a GitHub Actions workflow don't trigger other workflows
         # by design, so we have to manually ping code owners here.

.github/workflows/scripts/add-labels.sh

@@ -23,13 +23,11 @@ COLORS["testbed"]="#336600"
 
 FALLBACK_COLOR="#999966"
 
-CUR_DIRECTORY=$(dirname "$0")
-COMPONENTS=$(sh "${CUR_DIRECTORY}/get-components.sh")
-
-for COMPONENT in ${COMPONENTS}; do
-    TYPE=$(echo "${COMPONENT}" | cut -f1 -d '/' )
-    LABEL_NAME=$(echo "${COMPONENT}" | sed -E 's%^(.+)/(.+)\1%\1/\2%')
+COMPONENTS=$(awk '/^[^#]/ { print $2 }' .github/component_labels.txt)
 
+for LABEL_NAME in ${COMPONENTS}; do
+    TYPE=$(echo "${LABEL_NAME}" | cut -f1 -d '/' )
+    
     if (( "${#LABEL_NAME}" > 50 )); then
         echo "'${LABEL_NAME}' exceeds GitHubs 50-character limit on labels, skipping"
         continue

.github/workflows/scripts/generate-component-labels.sh

@@ -45,7 +45,7 @@ for ISSUE in ${ISSUES}; do
     LABELS=$(gh issue view "${ISSUE}" --json labels --jq '.labels.[].name')
 
     for LABEL in ${LABELS}; do
-        COMPONENT="${LABEL}"
+        COMPONENT=$(awk -v path="${LABEL}" '$1 == path || $2 == path {print $1}' .github/component_labels.txt)
         OWNERS=$(COMPONENT=${LABEL} bash "${CUR_DIRECTORY}/get-codeowners.sh")
 
         if [[ -z "${OWNERS}" ]]; then

.github/workflows/scripts/mark-issues-as-stale.sh

@@ -13,7 +13,7 @@ if [[ -z "${COMPONENT:-}" || -z "${ISSUE:-}" ]]; then
 fi
 
 CUR_DIRECTORY=$(dirname "$0")
-
+COMPONENT=$(awk -v path="${COMPONENT}" 'index($1, path) > 0 || index($2, path) > 0 {print $1}' .github/component_labels.txt)
 OWNERS=$(COMPONENT="${COMPONENT}" bash "${CUR_DIRECTORY}/get-codeowners.sh")
 
 if [[ -z "${OWNERS}" ]]; then

.github/workflows/scripts/ping-codeowners-issues.sh

@@ -33,11 +33,11 @@ if [[ -n "${TITLE_COMPONENT}" && ! ("${TITLE_COMPONENT}" =~ " ") ]]; then
   if [[ -n "${CODEOWNERS}" ]]; then
     PING_LINES+="- ${TITLE_COMPONENT}: ${CODEOWNERS}\n"
     PINGED_COMPONENTS["${TITLE_COMPONENT}"]=1
-
-    if (( "${#TITLE_COMPONENT}" <= 50 )); then
-      LABELS+="${TITLE_COMPONENT}"
+    LABEL_NAME=$(awk -v path="${COMPONENT}" 'index($1, path) > 0 || index($2, path) > 0 {print $2}' .github/component_labels.txt)
+    if (( "${#LABEL_NAME}" <= 50 )); then
+      LABELS+="${LABEL_NAME}"
     else
-      echo "'${TITLE_COMPONENT}' exceeds GitHub's 50-character limit, skipping adding a label"
+      echo "'${LABEL_NAME}' exceeds GitHub's 50-character limit, skipping adding a label"
     fi
   fi
 fi
@@ -55,16 +55,16 @@ for COMPONENT in ${BODY_COMPONENTS}; do
 
     PING_LINES+="- ${COMPONENT}: ${CODEOWNERS}\n"
     PINGED_COMPONENTS["${COMPONENT}"]=1
-
-    if (( "${#COMPONENT}" > 50 )); then
-      echo "'${COMPONENT}' exceeds GitHub's 50-character limit on labels, skipping adding a label"
+    LABEL_NAME=$(awk -v path="${COMPONENT}" 'index($1, path) > 0 || index($2, path) > 0 {print $2}' .github/component_labels.txt)
+    if (( "${#LABEL_NAME}" > 50 )); then
+      echo "'${LABEL_NAME}' exceeds GitHub's 50-character limit on labels, skipping adding a label"
       continue
     fi
 
     if [[ -n "${LABELS}" ]]; then
       LABELS+=","
     fi
-    LABELS+="${COMPONENT}"
+    LABELS+="${LABEL_NAME}"
   fi
 done
 

.github/workflows/scripts/ping-codeowners-on-new-issue.sh

@@ -114,6 +114,31 @@ stability-tests: otelcontribcol
 	@echo Stability tests are disabled until we have a stable performance environment.
 	@echo To enable the tests replace this echo by $(MAKE) -C testbed run-stability-tests
 
+.PHONY: genlabels
+genlabels:
+	@echo "Generating path-to-label mappings..."
+	@echo "# This file is auto-generated. Do not edit manually." > .github/component_labels.txt
+	@grep -E '^[A-Za-z0-9/]' .github/CODEOWNERS | \
+		awk '{ print $$1 }' | \
+		sed -E 's%(.+)/$$%\1%' | \
+		while read -r COMPONENT; do \
+			LABEL_NAME=$$(printf '%s\n' "$${COMPONENT}" | sed -E 's%^(.+)/(.+)\1%\1/\2%'); \
+			if (( $${#LABEL_NAME} > 50 )); then \
+				OIFS=$${IFS}; \
+				IFS='/'; \
+				for SEGMENT in $${COMPONENT}; do \
+					r="/$${SEGMENT}\$$"; \
+					if [[ "$${COMPONENT}" =~ $${r} ]]; then \
+						break; \
+					fi; \
+					LABEL_NAME=$$(echo "$${LABEL_NAME}" | sed -E "s%^(.+)$${SEGMENT}\$$%\1%"); \
+				done; \
+				IFS=$${OIFS}; \
+			fi; \
+			echo "$${COMPONENT} $${LABEL_NAME}" >> .github/component_labels.txt; \
+		done
+	@echo "Labels generated and saved to .github/component_labels.txt"
+
 .PHONY: gogci
 gogci:
 	$(MAKE) $(FOR_GROUP_TARGET) TARGET="gci"
@@ -348,6 +373,7 @@ gendistributions: $(GITHUBGEN)
 
 .PHONY: update-codeowners
 update-codeowners: generate gengithub
+	$(MAKE) genlabels
 
 FILENAME?=$(shell git branch --show-current)
 .PHONY: chlog-new