ingestr 0.13.39__tar.gz → 0.13.40__tar.gz

{ingestr-0.13.39 → ingestr-0.13.40}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: ingestr
-Version: 0.13.39
+Version: 0.13.40
 Summary: ingestr is a command-line application that ingests data from various sources and stores them in any database.
 Project-URL: Homepage, https://github.com/bruin-data/ingestr
 Project-URL: Issues, https://github.com/bruin-data/ingestr/issues
@@ -50,6 +50,8 @@ Requires-Dist: dlt==1.10.0
 Requires-Dist: dnspython==2.7.0
 Requires-Dist: duckdb-engine==0.17.0
 Requires-Dist: duckdb==1.2.1
+Requires-Dist: elastic-transport==8.17.1
+Requires-Dist: elasticsearch==8.10.1
 Requires-Dist: et-xmlfile==2.0.0
 Requires-Dist: facebook-business==20.0.0
 Requires-Dist: filelock==3.17.0

{ingestr-0.13.39 → ingestr-0.13.40}/docs/.vitepress/config.mjs

@@ -74,6 +74,7 @@ export default defineConfig({
               { text: "Databricks", link: "/supported-sources/databricks.md" },
               { text: "DuckDB", link: "/supported-sources/duckdb.md" },
               { text: "DynamoDB", link: "/supported-sources/dynamodb.md" },
+              { text: "Elasticsearch", link: "/supported-sources/elasticsearch.md" },
               {
                 text: "Google BigQuery",
                 link: "/supported-sources/bigquery.md",

ingestr-0.13.40/docs/supported-sources/elasticsearch.md

@@ -0,0 +1,35 @@
+# Elasticsearch
+[Elasticsearch](https://www.elastic.co/elasticsearch) is a distributed, RESTful search and analytics engine designed for fast and scalable data retrieval.
+
+ingestr supports Elasticsearch as a source.
+
+## URI format
+The URI format for Elasticsearch is as follows:
+
+```plaintext
+elasticsearch://username:password@host:port?secure=<secure>&verify_certs=<verify_certs>
+```
+
+URI parameters:
+- `username`: The username used to authenticate with Elasticsearch.
+- `password`: The password associated with the specified username.
+- `host`: The host address of the Elasticsearch server.
+- `port`: The port number used by the Elasticsearch server.
+-  `secure`: Enables HTTPS when set to true. By default, it is true.
+- `verify_certs`: Verifies TLS certificates when set to true. By default, it is true.
+
+Source Table
+
+`<index-name>`: Fetches all available documents from the specified index.
+
+```ingestr ingest \
+    --source-uri "elasticsearch://elastic:changeme@localhost:9200?secure=false&verify_certs=false" \
+    --source-table 'test-index' \
+    --dest-uri "duckdb:///users.duckdb" \
+    --dest-table 'dest.users_detail'
+```
+
+This command retrieves all documents from the test-index in Elasticsearch and copy them to the dest.users_detail table in DuckDB.
+
+<img alt="ingestion_elasticsearch_img" src="../media/ingestion_elasticsearch_img.png" />
+

ingestr-0.13.40/ingestr/src/buildinfo.py

@@ -0,0 +1 @@
+version = "v0.13.40"

ingestr-0.13.40/ingestr/src/elasticsearch/__init__.py

@@ -0,0 +1,80 @@
+from datetime import date, datetime
+from typing import Any, Optional
+
+import dlt
+import pendulum
+from dlt.common.time import ensure_pendulum_datetime
+from pendulum import parse
+
+from elasticsearch import Elasticsearch
+
+
+@dlt.source
+def elasticsearch_source(
+    connection_url: str,
+    index: str,
+    verify_certs: bool,
+    incremental: Optional[dlt.sources.incremental] = None,
+):
+    client = Elasticsearch(connection_url, verify_certs=verify_certs)
+
+    @dlt.resource(
+        name=index, primary_key="id", write_disposition="merge", incremental=incremental
+    )
+    def get_documents(incremental=incremental):
+        body = {"query": {"match_all": {}}}
+
+        if incremental:
+            start_value = incremental.last_value
+            range_filter = {"gte": start_value}
+            if incremental.end_value is not None:
+                range_filter["lt"] = incremental.end_value
+            body = {"query": {"range": {incremental.cursor_path: range_filter}}}
+
+        page = client.search(index=index, scroll="5m", size=5, body=body)
+
+        sid = page["_scroll_id"]
+        hits = page["hits"]["hits"]
+
+        if not hits:
+            return
+
+        # fetching first page (via .search)
+        for doc in hits:
+            doc_data = {"id": doc["_id"], **doc["_source"]}
+            if incremental:
+                doc_data[incremental.cursor_path] = convert_elasticsearch_objs(
+                    doc_data[incremental.cursor_path]
+                )
+            yield doc_data
+
+        while True:
+            # fetching page 2 and other pages (via .scroll)
+            page = client.scroll(scroll_id=sid, scroll="5m")
+            sid = page["_scroll_id"]
+            hits = page["hits"]["hits"]
+            if not hits:
+                break
+            for doc in hits:
+                doc_data = {"id": doc["_id"], **doc["_source"]}
+                if incremental:
+                    doc_data[incremental.cursor_path] = convert_elasticsearch_objs(
+                        doc_data[incremental.cursor_path]
+                    )
+                yield doc_data
+
+        client.clear_scroll(scroll_id=sid)
+
+    return get_documents
+
+
+def convert_elasticsearch_objs(value: Any) -> Any:
+    if isinstance(value, str):
+        parsed_date = parse(value, strict=False)
+        if parsed_date is not None:
+            if isinstance(
+                parsed_date,
+                (pendulum.DateTime, pendulum.Date, datetime, date, str, float, int),
+            ):
+                return ensure_pendulum_datetime(parsed_date)
+    return value

{ingestr-0.13.39 → ingestr-0.13.40}/ingestr/src/factory.py

@@ -28,6 +28,7 @@ from ingestr.src.sources import (
     AsanaSource,
     ChessSource,
     DynamoDBSource,
+    ElasticsearchSource,
     FacebookAdsSource,
     FrankfurterSource,
     FreshdeskSource,
@@ -153,6 +154,7 @@ class SourceDestinationFactory:
         "frankfurter": FrankfurterSource,
         "freshdesk": FreshdeskSource,
         "phantombuster": PhantombusterSource,
+        "elasticsearch": ElasticsearchSource,
     }
     destinations: Dict[str, Type[DestinationProtocol]] = {
         "bigquery": BigQueryDestination,

{ingestr-0.13.39 → ingestr-0.13.40}/ingestr/src/sources.py

@@ -2298,3 +2298,53 @@ class PhantombusterSource:
             start_date=start_date,
             end_date=end_date,
         ).with_resources(table_name)
+
+
+class ElasticsearchSource:
+    def handles_incrementality(self) -> bool:
+        return False
+
+    def dlt_source(self, uri: str, table: str, **kwargs):
+        from ingestr.src.elasticsearch import elasticsearch_source
+
+        incremental = None
+        if kwargs.get("incremental_key"):
+            start_value = kwargs.get("interval_start")
+            end_value = kwargs.get("interval_end")
+
+            incremental = dlt_incremental(
+                kwargs.get("incremental_key", ""),
+                initial_value=start_value,
+                end_value=end_value,
+                range_end="closed",
+                range_start="closed",
+            )
+
+        # elasticsearch://localhost:9200?secure=true&verify_certs=false
+        parsed = urlparse(uri)
+
+        index = table
+        if not index:
+            raise ValueError("Table name must be provided which is the index name in elasticsearch")
+
+        query_params = parsed.query
+        params = parse_qs(query_params)
+
+        secure = True
+        if "secure" in params:
+            secure = params["secure"][0].capitalize() == "True"
+
+        verify_certs = True
+        if "verify_certs" in params:
+            verify_certs = params["verify_certs"][0].capitalize() == "True"
+
+        scheme = "https" if secure else "http"
+        netloc = parsed.netloc
+        connection_url = f"{scheme}://{netloc}"
+
+        return elasticsearch_source(
+            connection_url=connection_url,
+            index=index,
+            verify_certs=verify_certs,
+            incremental=incremental,
+        ).with_resources(table)

{ingestr-0.13.39 → ingestr-0.13.40}/requirements.in

@@ -48,4 +48,5 @@ clickhouse-sqlalchemy==0.2.7
 zstd==1.5.6.5
 ibm-db==3.2.6; platform_machine != "aarch64"
 ibm-db-sa==0.4.1; platform_machine != "aarch64"
-aiohttp>=3.11.15
+aiohttp>=3.11.15
+elasticsearch==8.10.1

{ingestr-0.13.39 → ingestr-0.13.40}/requirements.txt

@@ -51,6 +51,7 @@ cachetools==5.5.2
 certifi==2025.1.31
     # via
     #   clickhouse-connect
+    #   elastic-transport
     #   requests
     #   snowflake-connector-python
 cffi==1.17.1
@@ -104,6 +105,10 @@ duckdb==1.2.1
     #   duckdb-engine
 duckdb-engine==0.17.0
     # via -r requirements.in
+elastic-transport==8.17.1
+    # via elasticsearch
+elasticsearch==8.10.1
+    # via -r requirements.in
 et-xmlfile==2.0.0
     # via openpyxl
 facebook-business==20.0.0
@@ -553,6 +558,7 @@ urllib3==2.3.0
     #   botocore
     #   clickhouse-connect
     #   databricks-sql-connector
+    #   elastic-transport
     #   pyairtable
     #   requests
     #   types-requests

{ingestr-0.13.39 → ingestr-0.13.40}/requirements_arm64.txt

@@ -51,6 +51,7 @@ cachetools==5.5.2
 certifi==2025.1.31
     # via
     #   clickhouse-connect
+    #   elastic-transport
     #   requests
     #   snowflake-connector-python
 cffi==1.17.1
@@ -104,6 +105,10 @@ duckdb==1.2.1
     #   duckdb-engine
 duckdb-engine==0.17.0
     # via -r requirements.in
+elastic-transport==8.17.1
+    # via elasticsearch
+elasticsearch==8.10.1
+    # via -r requirements.in
 et-xmlfile==2.0.0
     # via openpyxl
 facebook-business==20.0.0
@@ -549,6 +554,7 @@ urllib3==2.3.0
     #   botocore
     #   clickhouse-connect
     #   databricks-sql-connector
+    #   elastic-transport
     #   pyairtable
     #   requests
     #   types-requests

ingestr-0.13.39/ingestr/src/buildinfo.py

@@ -1 +0,0 @@
-version = "v0.13.39"