From 14d6db605b26b62638852b8a2dc0d6e7a3c0104c Mon Sep 17 00:00:00 2001
From: Remi Dettai <rdettai@gmail.com>
Date: Wed, 17 Jan 2024 14:40:33 +0000
Subject: [PATCH] Apply new versioning and skip hdfs decompression

---
 .github/workflows/publish_lambda_packages.yml | 12 ++----------
 distribution/lambda/Makefile                  |  9 ++++++++-
 distribution/lambda/cdk/cli.py                | 10 ++++------
 3 files changed, 14 insertions(+), 17 deletions(-)

diff --git a/.github/workflows/publish_lambda_packages.yml b/.github/workflows/publish_lambda_packages.yml
index e7411ebddab..6b511183dac 100644
--- a/.github/workflows/publish_lambda_packages.yml
+++ b/.github/workflows/publish_lambda_packages.yml
@@ -3,12 +3,7 @@ name: Build and publish AWS Lambda packages
 on:
   push:
     tags:
-      - "v*"
-      - "lambda-v*"
-  workflow_dispatch:
-
-env:
-  PRERELEASE_VERSION_NAME: beta
+      - "lambda-beta-*"
 
 jobs:
   build-lambdas:
@@ -28,9 +23,6 @@ jobs:
       - name: Extract asset version of release
         run: echo "QW_LAMBDA_VERSION=${GITHUB_REF/refs\/tags\//}" >> $GITHUB_ENV
         if: ${{ github.event_name == 'push' }}
-      - name: Setting version as prerelease
-        run: echo "QW_LAMBDA_VERSION=${{ env.PRERELEASE_VERSION_NAME }}" >> $GITHUB_ENV
-        if: ${{ github.event_name != 'push' }}
       - name: Retrieve and export commit date, hash, and tags
         run: |
             echo "QW_COMMIT_DATE=$(TZ=UTC0 git log -1 --format=%cd --date=format-local:%Y-%m-%dT%H:%M:%SZ)" >> $GITHUB_ENV
@@ -57,4 +49,4 @@ jobs:
           file: ${{ env.SEARCHER_PACKAGE_LOCATION }};${{ env.INDEXER_PACKAGE_LOCATION }}
           overwrite: true
           draft: true
-          tag_name: aws-lambda-${{ env.QW_LAMBDA_VERSION }}
+          tag_name: aws-${{ env.QW_LAMBDA_VERSION }}
diff --git a/distribution/lambda/Makefile b/distribution/lambda/Makefile
index 701e9ba94b1..4dfd1d1b076 100644
--- a/distribution/lambda/Makefile
+++ b/distribution/lambda/Makefile
@@ -3,7 +3,8 @@
 SHELL := bash
 .SHELLFLAGS := -eu -o pipefail -c
 
-QW_LAMBDA_VERSION?=beta
+# Update this when cutting a new release
+QW_LAMBDA_VERSION?=beta-01
 PACKAGE_BASE_URL=https://github.com/quickwit-oss/quickwit/releases/download/aws-lambda-$(QW_LAMBDA_VERSION)/
 SEARCHER_PACKAGE_FILE=quickwit-lambda-searcher-$(QW_LAMBDA_VERSION)-x86_64.zip
 INDEXER_PACKAGE_FILE=quickwit-lambda-indexer-$(QW_LAMBDA_VERSION)-x86_64.zip
@@ -36,10 +37,16 @@ package:
 	  cp -u ../../quickwit/target/lambda/indexer/bootstrap.zip $(INDEXER_PACKAGE_PATH)
 	else
 	  if ! [ -f $(SEARCHER_PACKAGE_PATH) ]; then
+	  	echo "Downloading package $(PACKAGE_BASE_URL)$(SEARCHER_PACKAGE_FILE)"
 	    curl -C - -Ls -o $(SEARCHER_PACKAGE_PATH) $(PACKAGE_BASE_URL)$(SEARCHER_PACKAGE_FILE)
+	  else
+	  	echo "Using cached package $(SEARCHER_PACKAGE_PATH)"
 	  fi
 	  if ! [ -f $(INDEXER_PACKAGE_PATH) ]; then
+	  	echo "Downloading package $(PACKAGE_BASE_URL)$(INDEXER_PACKAGE_FILE)"
 	  	curl -C - -Ls -o $(INDEXER_PACKAGE_PATH) $(PACKAGE_BASE_URL)$(INDEXER_PACKAGE_FILE)
+	  else
+	  	echo "Using cached package $(INDEXER_PACKAGE_PATH)"
 	  fi
 	fi
 
diff --git a/distribution/lambda/cdk/cli.py b/distribution/lambda/cdk/cli.py
index 4bb9f5b3de6..ce2fe4cf75d 100644
--- a/distribution/lambda/cdk/cli.py
+++ b/distribution/lambda/cdk/cli.py
@@ -24,8 +24,7 @@
 region = os.environ["CDK_REGION"]
 
 example_host = "quickwit-datasets-public.s3.amazonaws.com"
-# the publicly hosted file is compressed and suffixed with ".gz"
-example_hdfs_file = "hdfs-logs-multitenants.json"
+example_hdfs_file = "hdfs-logs-multitenants.json.gz"
 INDEXING_BOTO_CONFIG = botocore.config.Config(
     retries={"max_attempts": 0}, read_timeout=60 * 15
 )
@@ -139,17 +138,16 @@ def upload_hdfs_src_file():
     except botocore.exceptions.ClientError as e:
         if e.response["Error"]["Code"] != "404":
             raise e
-    print(f"download dataset https://{example_host}/{example_hdfs_file}.gz")
+    print(f"download dataset https://{example_host}/{example_hdfs_file}")
     conn = http.client.HTTPSConnection(example_host)
-    conn.request("GET", f"/{example_hdfs_file}.gz")
+    conn.request("GET", f"/{example_hdfs_file}")
     response = conn.getresponse()
     if response.status != 200:
         print(f"Failed to fetch dataset")
         exit(1)
     with tempfile.NamedTemporaryFile() as tmp:
-        unzipped_resp = gzip.GzipFile(mode="rb", fileobj=response)
         while True:
-            chunk = unzipped_resp.read(1024 * 1024)
+            chunk = response.read(1024 * 1024)
             if len(chunk) == 0:
                 break
             tmp.write(chunk)