ingestr 0.13.51__tar.gz → 0.13.53__tar.gz

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.

Potentially problematic release.


This version of ingestr might be problematic. Click here for more details.

Files changed (289) hide show
  1. {ingestr-0.13.51 → ingestr-0.13.53}/.gitignore +1 -0
  2. {ingestr-0.13.51 → ingestr-0.13.53}/PKG-INFO +51 -4
  3. {ingestr-0.13.51 → ingestr-0.13.53}/README.md +42 -2
  4. {ingestr-0.13.51 → ingestr-0.13.53}/docs/.vitepress/config.mjs +2 -1
  5. ingestr-0.13.53/docs/media/cratedb-source.png +0 -0
  6. ingestr-0.13.53/docs/media/sftp.png +0 -0
  7. ingestr-0.13.53/docs/supported-sources/cratedb.md +80 -0
  8. {ingestr-0.13.51 → ingestr-0.13.53}/docs/supported-sources/mysql.md +3 -3
  9. ingestr-0.13.53/docs/supported-sources/sftp.md +43 -0
  10. {ingestr-0.13.51 → ingestr-0.13.53}/docs/supported-sources/solidgate.md +3 -2
  11. {ingestr-0.13.51 → ingestr-0.13.53}/docs/supported-sources/sqlite.md +1 -1
  12. {ingestr-0.13.51 → ingestr-0.13.53}/ingestr/main.py +19 -2
  13. ingestr-0.13.53/ingestr/src/buildinfo.py +1 -0
  14. {ingestr-0.13.51 → ingestr-0.13.53}/ingestr/src/destinations.py +30 -0
  15. {ingestr-0.13.51 → ingestr-0.13.53}/ingestr/src/factory.py +9 -1
  16. {ingestr-0.13.51 → ingestr-0.13.53}/ingestr/src/filters.py +14 -0
  17. {ingestr-0.13.51 → ingestr-0.13.53}/ingestr/src/solidgate/__init__.py +3 -3
  18. {ingestr-0.13.51 → ingestr-0.13.53}/ingestr/src/sources.py +55 -25
  19. {ingestr-0.13.51 → ingestr-0.13.53}/requirements.in +2 -0
  20. {ingestr-0.13.51 → ingestr-0.13.53}/requirements.txt +24 -2
  21. {ingestr-0.13.51 → ingestr-0.13.53}/requirements_arm64.txt +23 -1
  22. ingestr-0.13.51/ingestr/src/buildinfo.py +0 -1
  23. {ingestr-0.13.51 → ingestr-0.13.53}/.dockerignore +0 -0
  24. {ingestr-0.13.51 → ingestr-0.13.53}/.githooks/pre-commit-hook.sh +0 -0
  25. {ingestr-0.13.51 → ingestr-0.13.53}/.github/workflows/deploy-docs.yml +0 -0
  26. {ingestr-0.13.51 → ingestr-0.13.53}/.github/workflows/release.yml +0 -0
  27. {ingestr-0.13.51 → ingestr-0.13.53}/.github/workflows/secrets-scan.yml +0 -0
  28. {ingestr-0.13.51 → ingestr-0.13.53}/.github/workflows/tests.yml +0 -0
  29. {ingestr-0.13.51 → ingestr-0.13.53}/.gitleaksignore +0 -0
  30. {ingestr-0.13.51 → ingestr-0.13.53}/.python-version +0 -0
  31. {ingestr-0.13.51 → ingestr-0.13.53}/.vale.ini +0 -0
  32. {ingestr-0.13.51 → ingestr-0.13.53}/Dockerfile +0 -0
  33. {ingestr-0.13.51 → ingestr-0.13.53}/LICENSE.md +0 -0
  34. {ingestr-0.13.51 → ingestr-0.13.53}/Makefile +0 -0
  35. {ingestr-0.13.51 → ingestr-0.13.53}/docs/.vitepress/theme/custom.css +0 -0
  36. {ingestr-0.13.51 → ingestr-0.13.53}/docs/.vitepress/theme/index.js +0 -0
  37. {ingestr-0.13.51 → ingestr-0.13.53}/docs/commands/example-uris.md +0 -0
  38. {ingestr-0.13.51 → ingestr-0.13.53}/docs/commands/ingest.md +0 -0
  39. {ingestr-0.13.51 → ingestr-0.13.53}/docs/getting-started/core-concepts.md +0 -0
  40. {ingestr-0.13.51 → ingestr-0.13.53}/docs/getting-started/incremental-loading.md +0 -0
  41. {ingestr-0.13.51 → ingestr-0.13.53}/docs/getting-started/quickstart.md +0 -0
  42. {ingestr-0.13.51 → ingestr-0.13.53}/docs/getting-started/telemetry.md +0 -0
  43. {ingestr-0.13.51 → ingestr-0.13.53}/docs/index.md +0 -0
  44. {ingestr-0.13.51 → ingestr-0.13.53}/docs/media/applovin_max.png +0 -0
  45. {ingestr-0.13.51 → ingestr-0.13.53}/docs/media/athena.png +0 -0
  46. {ingestr-0.13.51 → ingestr-0.13.53}/docs/media/clickhouse_img.png +0 -0
  47. {ingestr-0.13.51 → ingestr-0.13.53}/docs/media/freshdesk_ingestion.png +0 -0
  48. {ingestr-0.13.51 → ingestr-0.13.53}/docs/media/gcp_spanner_ingestion.png +0 -0
  49. {ingestr-0.13.51 → ingestr-0.13.53}/docs/media/github.png +0 -0
  50. {ingestr-0.13.51 → ingestr-0.13.53}/docs/media/google_analytics_realtime_report.png +0 -0
  51. {ingestr-0.13.51 → ingestr-0.13.53}/docs/media/googleanalytics.png +0 -0
  52. {ingestr-0.13.51 → ingestr-0.13.53}/docs/media/ingestion_elasticsearch_img.png +0 -0
  53. {ingestr-0.13.51 → ingestr-0.13.53}/docs/media/kinesis.bigquery.png +0 -0
  54. {ingestr-0.13.51 → ingestr-0.13.53}/docs/media/linkedin_ads.png +0 -0
  55. {ingestr-0.13.51 → ingestr-0.13.53}/docs/media/personio.png +0 -0
  56. {ingestr-0.13.51 → ingestr-0.13.53}/docs/media/personio_duckdb.png +0 -0
  57. {ingestr-0.13.51 → ingestr-0.13.53}/docs/media/phantombuster.png +0 -0
  58. {ingestr-0.13.51 → ingestr-0.13.53}/docs/media/pipedrive.png +0 -0
  59. {ingestr-0.13.51 → ingestr-0.13.53}/docs/media/stripe_postgres.png +0 -0
  60. {ingestr-0.13.51 → ingestr-0.13.53}/docs/media/tiktok.png +0 -0
  61. {ingestr-0.13.51 → ingestr-0.13.53}/docs/supported-sources/adjust.md +0 -0
  62. {ingestr-0.13.51 → ingestr-0.13.53}/docs/supported-sources/airtable.md +0 -0
  63. {ingestr-0.13.51 → ingestr-0.13.53}/docs/supported-sources/applovin.md +0 -0
  64. {ingestr-0.13.51 → ingestr-0.13.53}/docs/supported-sources/applovin_max.md +0 -0
  65. {ingestr-0.13.51 → ingestr-0.13.53}/docs/supported-sources/appsflyer.md +0 -0
  66. {ingestr-0.13.51 → ingestr-0.13.53}/docs/supported-sources/appstore.md +0 -0
  67. {ingestr-0.13.51 → ingestr-0.13.53}/docs/supported-sources/asana.md +0 -0
  68. {ingestr-0.13.51 → ingestr-0.13.53}/docs/supported-sources/athena.md +0 -0
  69. {ingestr-0.13.51 → ingestr-0.13.53}/docs/supported-sources/attio.md +0 -0
  70. {ingestr-0.13.51 → ingestr-0.13.53}/docs/supported-sources/bigquery.md +0 -0
  71. {ingestr-0.13.51 → ingestr-0.13.53}/docs/supported-sources/chess.md +0 -0
  72. {ingestr-0.13.51 → ingestr-0.13.53}/docs/supported-sources/clickhouse.md +0 -0
  73. {ingestr-0.13.51 → ingestr-0.13.53}/docs/supported-sources/csv.md +0 -0
  74. {ingestr-0.13.51 → ingestr-0.13.53}/docs/supported-sources/custom_queries.md +0 -0
  75. {ingestr-0.13.51 → ingestr-0.13.53}/docs/supported-sources/databricks.md +0 -0
  76. {ingestr-0.13.51 → ingestr-0.13.53}/docs/supported-sources/db2.md +0 -0
  77. {ingestr-0.13.51 → ingestr-0.13.53}/docs/supported-sources/duckdb.md +0 -0
  78. {ingestr-0.13.51 → ingestr-0.13.53}/docs/supported-sources/dynamodb.md +0 -0
  79. {ingestr-0.13.51 → ingestr-0.13.53}/docs/supported-sources/elasticsearch.md +0 -0
  80. {ingestr-0.13.51 → ingestr-0.13.53}/docs/supported-sources/facebook-ads.md +0 -0
  81. {ingestr-0.13.51 → ingestr-0.13.53}/docs/supported-sources/frankfurter.md +0 -0
  82. {ingestr-0.13.51 → ingestr-0.13.53}/docs/supported-sources/freshdesk.md +0 -0
  83. {ingestr-0.13.51 → ingestr-0.13.53}/docs/supported-sources/gcs.md +0 -0
  84. {ingestr-0.13.51 → ingestr-0.13.53}/docs/supported-sources/github.md +0 -0
  85. {ingestr-0.13.51 → ingestr-0.13.53}/docs/supported-sources/google-ads.md +0 -0
  86. {ingestr-0.13.51 → ingestr-0.13.53}/docs/supported-sources/google_analytics.md +0 -0
  87. {ingestr-0.13.51 → ingestr-0.13.53}/docs/supported-sources/gorgias.md +0 -0
  88. {ingestr-0.13.51 → ingestr-0.13.53}/docs/supported-sources/gsheets.md +0 -0
  89. {ingestr-0.13.51 → ingestr-0.13.53}/docs/supported-sources/hubspot.md +0 -0
  90. {ingestr-0.13.51 → ingestr-0.13.53}/docs/supported-sources/kafka.md +0 -0
  91. {ingestr-0.13.51 → ingestr-0.13.53}/docs/supported-sources/kinesis.md +0 -0
  92. {ingestr-0.13.51 → ingestr-0.13.53}/docs/supported-sources/klaviyo.md +0 -0
  93. {ingestr-0.13.51 → ingestr-0.13.53}/docs/supported-sources/linkedin_ads.md +0 -0
  94. {ingestr-0.13.51 → ingestr-0.13.53}/docs/supported-sources/mongodb.md +0 -0
  95. {ingestr-0.13.51 → ingestr-0.13.53}/docs/supported-sources/mssql.md +0 -0
  96. {ingestr-0.13.51 → ingestr-0.13.53}/docs/supported-sources/notion.md +0 -0
  97. {ingestr-0.13.51 → ingestr-0.13.53}/docs/supported-sources/oracle.md +0 -0
  98. {ingestr-0.13.51 → ingestr-0.13.53}/docs/supported-sources/personio.md +0 -0
  99. {ingestr-0.13.51 → ingestr-0.13.53}/docs/supported-sources/phantombuster.md +0 -0
  100. {ingestr-0.13.51 → ingestr-0.13.53}/docs/supported-sources/pipedrive.md +0 -0
  101. {ingestr-0.13.51 → ingestr-0.13.53}/docs/supported-sources/postgres.md +0 -0
  102. {ingestr-0.13.51 → ingestr-0.13.53}/docs/supported-sources/redshift.md +0 -0
  103. {ingestr-0.13.51 → ingestr-0.13.53}/docs/supported-sources/s3.md +0 -0
  104. {ingestr-0.13.51 → ingestr-0.13.53}/docs/supported-sources/salesforce.md +0 -0
  105. {ingestr-0.13.51 → ingestr-0.13.53}/docs/supported-sources/sap-hana.md +0 -0
  106. {ingestr-0.13.51 → ingestr-0.13.53}/docs/supported-sources/shopify.md +0 -0
  107. {ingestr-0.13.51 → ingestr-0.13.53}/docs/supported-sources/slack.md +0 -0
  108. {ingestr-0.13.51 → ingestr-0.13.53}/docs/supported-sources/smartsheets.md +0 -0
  109. {ingestr-0.13.51 → ingestr-0.13.53}/docs/supported-sources/snowflake.md +0 -0
  110. {ingestr-0.13.51 → ingestr-0.13.53}/docs/supported-sources/spanner.md +0 -0
  111. {ingestr-0.13.51 → ingestr-0.13.53}/docs/supported-sources/stripe.md +0 -0
  112. {ingestr-0.13.51 → ingestr-0.13.53}/docs/supported-sources/tiktok-ads.md +0 -0
  113. {ingestr-0.13.51 → ingestr-0.13.53}/docs/supported-sources/zendesk.md +0 -0
  114. {ingestr-0.13.51 → ingestr-0.13.53}/docs/tutorials/load-kinesis-bigquery.md +0 -0
  115. {ingestr-0.13.51 → ingestr-0.13.53}/docs/tutorials/load-personio-duckdb.md +0 -0
  116. {ingestr-0.13.51 → ingestr-0.13.53}/docs/tutorials/load-stripe-postgres.md +0 -0
  117. {ingestr-0.13.51 → ingestr-0.13.53}/ingestr/conftest.py +0 -0
  118. {ingestr-0.13.51 → ingestr-0.13.53}/ingestr/src/.gitignore +0 -0
  119. {ingestr-0.13.51 → ingestr-0.13.53}/ingestr/src/adjust/__init__.py +0 -0
  120. {ingestr-0.13.51 → ingestr-0.13.53}/ingestr/src/adjust/adjust_helpers.py +0 -0
  121. {ingestr-0.13.51 → ingestr-0.13.53}/ingestr/src/airtable/__init__.py +0 -0
  122. {ingestr-0.13.51 → ingestr-0.13.53}/ingestr/src/applovin/__init__.py +0 -0
  123. {ingestr-0.13.51 → ingestr-0.13.53}/ingestr/src/applovin_max/__init__.py +0 -0
  124. {ingestr-0.13.51 → ingestr-0.13.53}/ingestr/src/appsflyer/__init__.py +0 -0
  125. {ingestr-0.13.51 → ingestr-0.13.53}/ingestr/src/appsflyer/client.py +0 -0
  126. {ingestr-0.13.51 → ingestr-0.13.53}/ingestr/src/appstore/__init__.py +0 -0
  127. {ingestr-0.13.51 → ingestr-0.13.53}/ingestr/src/appstore/client.py +0 -0
  128. {ingestr-0.13.51 → ingestr-0.13.53}/ingestr/src/appstore/errors.py +0 -0
  129. {ingestr-0.13.51 → ingestr-0.13.53}/ingestr/src/appstore/models.py +0 -0
  130. {ingestr-0.13.51 → ingestr-0.13.53}/ingestr/src/appstore/resources.py +0 -0
  131. {ingestr-0.13.51 → ingestr-0.13.53}/ingestr/src/arrow/__init__.py +0 -0
  132. {ingestr-0.13.51 → ingestr-0.13.53}/ingestr/src/asana_source/__init__.py +0 -0
  133. {ingestr-0.13.51 → ingestr-0.13.53}/ingestr/src/asana_source/helpers.py +0 -0
  134. {ingestr-0.13.51 → ingestr-0.13.53}/ingestr/src/asana_source/settings.py +0 -0
  135. {ingestr-0.13.51 → ingestr-0.13.53}/ingestr/src/attio/__init__.py +0 -0
  136. {ingestr-0.13.51 → ingestr-0.13.53}/ingestr/src/attio/helpers.py +0 -0
  137. {ingestr-0.13.51 → ingestr-0.13.53}/ingestr/src/blob.py +0 -0
  138. {ingestr-0.13.51 → ingestr-0.13.53}/ingestr/src/chess/__init__.py +0 -0
  139. {ingestr-0.13.51 → ingestr-0.13.53}/ingestr/src/chess/helpers.py +0 -0
  140. {ingestr-0.13.51 → ingestr-0.13.53}/ingestr/src/chess/settings.py +0 -0
  141. {ingestr-0.13.51 → ingestr-0.13.53}/ingestr/src/collector/spinner.py +0 -0
  142. {ingestr-0.13.51 → ingestr-0.13.53}/ingestr/src/dynamodb/__init__.py +0 -0
  143. {ingestr-0.13.51 → ingestr-0.13.53}/ingestr/src/elasticsearch/__init__.py +0 -0
  144. {ingestr-0.13.51 → ingestr-0.13.53}/ingestr/src/errors.py +0 -0
  145. {ingestr-0.13.51 → ingestr-0.13.53}/ingestr/src/facebook_ads/__init__.py +0 -0
  146. {ingestr-0.13.51 → ingestr-0.13.53}/ingestr/src/facebook_ads/exceptions.py +0 -0
  147. {ingestr-0.13.51 → ingestr-0.13.53}/ingestr/src/facebook_ads/helpers.py +0 -0
  148. {ingestr-0.13.51 → ingestr-0.13.53}/ingestr/src/facebook_ads/settings.py +0 -0
  149. {ingestr-0.13.51 → ingestr-0.13.53}/ingestr/src/filesystem/__init__.py +0 -0
  150. {ingestr-0.13.51 → ingestr-0.13.53}/ingestr/src/filesystem/helpers.py +0 -0
  151. {ingestr-0.13.51 → ingestr-0.13.53}/ingestr/src/filesystem/readers.py +0 -0
  152. {ingestr-0.13.51 → ingestr-0.13.53}/ingestr/src/frankfurter/__init__.py +0 -0
  153. {ingestr-0.13.51 → ingestr-0.13.53}/ingestr/src/frankfurter/helpers.py +0 -0
  154. {ingestr-0.13.51 → ingestr-0.13.53}/ingestr/src/freshdesk/__init__.py +0 -0
  155. {ingestr-0.13.51 → ingestr-0.13.53}/ingestr/src/freshdesk/freshdesk_client.py +0 -0
  156. {ingestr-0.13.51 → ingestr-0.13.53}/ingestr/src/freshdesk/settings.py +0 -0
  157. {ingestr-0.13.51 → ingestr-0.13.53}/ingestr/src/github/__init__.py +0 -0
  158. {ingestr-0.13.51 → ingestr-0.13.53}/ingestr/src/github/helpers.py +0 -0
  159. {ingestr-0.13.51 → ingestr-0.13.53}/ingestr/src/github/queries.py +0 -0
  160. {ingestr-0.13.51 → ingestr-0.13.53}/ingestr/src/github/settings.py +0 -0
  161. {ingestr-0.13.51 → ingestr-0.13.53}/ingestr/src/google_ads/__init__.py +0 -0
  162. {ingestr-0.13.51 → ingestr-0.13.53}/ingestr/src/google_ads/field.py +0 -0
  163. {ingestr-0.13.51 → ingestr-0.13.53}/ingestr/src/google_ads/metrics.py +0 -0
  164. {ingestr-0.13.51 → ingestr-0.13.53}/ingestr/src/google_ads/predicates.py +0 -0
  165. {ingestr-0.13.51 → ingestr-0.13.53}/ingestr/src/google_ads/reports.py +0 -0
  166. {ingestr-0.13.51 → ingestr-0.13.53}/ingestr/src/google_analytics/__init__.py +0 -0
  167. {ingestr-0.13.51 → ingestr-0.13.53}/ingestr/src/google_analytics/helpers.py +0 -0
  168. {ingestr-0.13.51 → ingestr-0.13.53}/ingestr/src/google_sheets/README.md +0 -0
  169. {ingestr-0.13.51 → ingestr-0.13.53}/ingestr/src/google_sheets/__init__.py +0 -0
  170. {ingestr-0.13.51 → ingestr-0.13.53}/ingestr/src/google_sheets/helpers/__init__.py +0 -0
  171. {ingestr-0.13.51 → ingestr-0.13.53}/ingestr/src/google_sheets/helpers/api_calls.py +0 -0
  172. {ingestr-0.13.51 → ingestr-0.13.53}/ingestr/src/google_sheets/helpers/data_processing.py +0 -0
  173. {ingestr-0.13.51 → ingestr-0.13.53}/ingestr/src/gorgias/__init__.py +0 -0
  174. {ingestr-0.13.51 → ingestr-0.13.53}/ingestr/src/gorgias/helpers.py +0 -0
  175. {ingestr-0.13.51 → ingestr-0.13.53}/ingestr/src/http_client.py +0 -0
  176. {ingestr-0.13.51 → ingestr-0.13.53}/ingestr/src/hubspot/__init__.py +0 -0
  177. {ingestr-0.13.51 → ingestr-0.13.53}/ingestr/src/hubspot/helpers.py +0 -0
  178. {ingestr-0.13.51 → ingestr-0.13.53}/ingestr/src/hubspot/settings.py +0 -0
  179. {ingestr-0.13.51 → ingestr-0.13.53}/ingestr/src/kafka/__init__.py +0 -0
  180. {ingestr-0.13.51 → ingestr-0.13.53}/ingestr/src/kafka/helpers.py +0 -0
  181. {ingestr-0.13.51 → ingestr-0.13.53}/ingestr/src/kinesis/__init__.py +0 -0
  182. {ingestr-0.13.51 → ingestr-0.13.53}/ingestr/src/kinesis/helpers.py +0 -0
  183. {ingestr-0.13.51 → ingestr-0.13.53}/ingestr/src/klaviyo/__init__.py +0 -0
  184. {ingestr-0.13.51 → ingestr-0.13.53}/ingestr/src/klaviyo/client.py +0 -0
  185. {ingestr-0.13.51 → ingestr-0.13.53}/ingestr/src/klaviyo/helpers.py +0 -0
  186. {ingestr-0.13.51 → ingestr-0.13.53}/ingestr/src/linkedin_ads/__init__.py +0 -0
  187. {ingestr-0.13.51 → ingestr-0.13.53}/ingestr/src/linkedin_ads/dimension_time_enum.py +0 -0
  188. {ingestr-0.13.51 → ingestr-0.13.53}/ingestr/src/linkedin_ads/helpers.py +0 -0
  189. {ingestr-0.13.51 → ingestr-0.13.53}/ingestr/src/loader.py +0 -0
  190. {ingestr-0.13.51 → ingestr-0.13.53}/ingestr/src/mongodb/__init__.py +0 -0
  191. {ingestr-0.13.51 → ingestr-0.13.53}/ingestr/src/mongodb/helpers.py +0 -0
  192. {ingestr-0.13.51 → ingestr-0.13.53}/ingestr/src/notion/__init__.py +0 -0
  193. {ingestr-0.13.51 → ingestr-0.13.53}/ingestr/src/notion/helpers/__init__.py +0 -0
  194. {ingestr-0.13.51 → ingestr-0.13.53}/ingestr/src/notion/helpers/client.py +0 -0
  195. {ingestr-0.13.51 → ingestr-0.13.53}/ingestr/src/notion/helpers/database.py +0 -0
  196. {ingestr-0.13.51 → ingestr-0.13.53}/ingestr/src/notion/settings.py +0 -0
  197. {ingestr-0.13.51 → ingestr-0.13.53}/ingestr/src/partition.py +0 -0
  198. {ingestr-0.13.51 → ingestr-0.13.53}/ingestr/src/personio/__init__.py +0 -0
  199. {ingestr-0.13.51 → ingestr-0.13.53}/ingestr/src/personio/helpers.py +0 -0
  200. {ingestr-0.13.51 → ingestr-0.13.53}/ingestr/src/phantombuster/__init__.py +0 -0
  201. {ingestr-0.13.51 → ingestr-0.13.53}/ingestr/src/phantombuster/client.py +0 -0
  202. {ingestr-0.13.51 → ingestr-0.13.53}/ingestr/src/pipedrive/__init__.py +0 -0
  203. {ingestr-0.13.51 → ingestr-0.13.53}/ingestr/src/pipedrive/helpers/__init__.py +0 -0
  204. {ingestr-0.13.51 → ingestr-0.13.53}/ingestr/src/pipedrive/helpers/custom_fields_munger.py +0 -0
  205. {ingestr-0.13.51 → ingestr-0.13.53}/ingestr/src/pipedrive/helpers/pages.py +0 -0
  206. {ingestr-0.13.51 → ingestr-0.13.53}/ingestr/src/pipedrive/settings.py +0 -0
  207. {ingestr-0.13.51 → ingestr-0.13.53}/ingestr/src/pipedrive/typing.py +0 -0
  208. {ingestr-0.13.51 → ingestr-0.13.53}/ingestr/src/resource.py +0 -0
  209. {ingestr-0.13.51 → ingestr-0.13.53}/ingestr/src/salesforce/__init__.py +0 -0
  210. {ingestr-0.13.51 → ingestr-0.13.53}/ingestr/src/salesforce/helpers.py +0 -0
  211. {ingestr-0.13.51 → ingestr-0.13.53}/ingestr/src/shopify/__init__.py +0 -0
  212. {ingestr-0.13.51 → ingestr-0.13.53}/ingestr/src/shopify/exceptions.py +0 -0
  213. {ingestr-0.13.51 → ingestr-0.13.53}/ingestr/src/shopify/helpers.py +0 -0
  214. {ingestr-0.13.51 → ingestr-0.13.53}/ingestr/src/shopify/settings.py +0 -0
  215. {ingestr-0.13.51 → ingestr-0.13.53}/ingestr/src/slack/__init__.py +0 -0
  216. {ingestr-0.13.51 → ingestr-0.13.53}/ingestr/src/slack/helpers.py +0 -0
  217. {ingestr-0.13.51 → ingestr-0.13.53}/ingestr/src/slack/settings.py +0 -0
  218. {ingestr-0.13.51 → ingestr-0.13.53}/ingestr/src/smartsheets/__init__.py +0 -0
  219. {ingestr-0.13.51 → ingestr-0.13.53}/ingestr/src/solidgate/helpers.py +0 -0
  220. {ingestr-0.13.51 → ingestr-0.13.53}/ingestr/src/sql_database/__init__.py +0 -0
  221. {ingestr-0.13.51 → ingestr-0.13.53}/ingestr/src/sql_database/callbacks.py +0 -0
  222. {ingestr-0.13.51 → ingestr-0.13.53}/ingestr/src/stripe_analytics/__init__.py +0 -0
  223. {ingestr-0.13.51 → ingestr-0.13.53}/ingestr/src/stripe_analytics/helpers.py +0 -0
  224. {ingestr-0.13.51 → ingestr-0.13.53}/ingestr/src/stripe_analytics/settings.py +0 -0
  225. {ingestr-0.13.51 → ingestr-0.13.53}/ingestr/src/table_definition.py +0 -0
  226. {ingestr-0.13.51 → ingestr-0.13.53}/ingestr/src/telemetry/event.py +0 -0
  227. {ingestr-0.13.51 → ingestr-0.13.53}/ingestr/src/testdata/fakebqcredentials.json +0 -0
  228. {ingestr-0.13.51 → ingestr-0.13.53}/ingestr/src/tiktok_ads/__init__.py +0 -0
  229. {ingestr-0.13.51 → ingestr-0.13.53}/ingestr/src/tiktok_ads/tiktok_helpers.py +0 -0
  230. {ingestr-0.13.51 → ingestr-0.13.53}/ingestr/src/time.py +0 -0
  231. {ingestr-0.13.51 → ingestr-0.13.53}/ingestr/src/version.py +0 -0
  232. {ingestr-0.13.51 → ingestr-0.13.53}/ingestr/src/zendesk/__init__.py +0 -0
  233. {ingestr-0.13.51 → ingestr-0.13.53}/ingestr/src/zendesk/helpers/__init__.py +0 -0
  234. {ingestr-0.13.51 → ingestr-0.13.53}/ingestr/src/zendesk/helpers/api_helpers.py +0 -0
  235. {ingestr-0.13.51 → ingestr-0.13.53}/ingestr/src/zendesk/helpers/credentials.py +0 -0
  236. {ingestr-0.13.51 → ingestr-0.13.53}/ingestr/src/zendesk/helpers/talk_api.py +0 -0
  237. {ingestr-0.13.51 → ingestr-0.13.53}/ingestr/src/zendesk/settings.py +0 -0
  238. {ingestr-0.13.51 → ingestr-0.13.53}/ingestr/testdata/.gitignore +0 -0
  239. {ingestr-0.13.51 → ingestr-0.13.53}/ingestr/testdata/create_replace.csv +0 -0
  240. {ingestr-0.13.51 → ingestr-0.13.53}/ingestr/testdata/delete_insert_expected.csv +0 -0
  241. {ingestr-0.13.51 → ingestr-0.13.53}/ingestr/testdata/delete_insert_part1.csv +0 -0
  242. {ingestr-0.13.51 → ingestr-0.13.53}/ingestr/testdata/delete_insert_part2.csv +0 -0
  243. {ingestr-0.13.51 → ingestr-0.13.53}/ingestr/testdata/merge_expected.csv +0 -0
  244. {ingestr-0.13.51 → ingestr-0.13.53}/ingestr/testdata/merge_part1.csv +0 -0
  245. {ingestr-0.13.51 → ingestr-0.13.53}/ingestr/testdata/merge_part2.csv +0 -0
  246. {ingestr-0.13.51 → ingestr-0.13.53}/ingestr/tests/unit/test_smartsheets.py +0 -0
  247. {ingestr-0.13.51 → ingestr-0.13.53}/package-lock.json +0 -0
  248. {ingestr-0.13.51 → ingestr-0.13.53}/package.json +0 -0
  249. {ingestr-0.13.51 → ingestr-0.13.53}/pyproject.toml +0 -0
  250. {ingestr-0.13.51 → ingestr-0.13.53}/requirements-dev.txt +0 -0
  251. {ingestr-0.13.51 → ingestr-0.13.53}/resources/demo.gif +0 -0
  252. {ingestr-0.13.51 → ingestr-0.13.53}/resources/demo.tape +0 -0
  253. {ingestr-0.13.51 → ingestr-0.13.53}/resources/ingestr.svg +0 -0
  254. {ingestr-0.13.51 → ingestr-0.13.53}/styles/Google/AMPM.yml +0 -0
  255. {ingestr-0.13.51 → ingestr-0.13.53}/styles/Google/Acronyms.yml +0 -0
  256. {ingestr-0.13.51 → ingestr-0.13.53}/styles/Google/Colons.yml +0 -0
  257. {ingestr-0.13.51 → ingestr-0.13.53}/styles/Google/Contractions.yml +0 -0
  258. {ingestr-0.13.51 → ingestr-0.13.53}/styles/Google/DateFormat.yml +0 -0
  259. {ingestr-0.13.51 → ingestr-0.13.53}/styles/Google/Ellipses.yml +0 -0
  260. {ingestr-0.13.51 → ingestr-0.13.53}/styles/Google/EmDash.yml +0 -0
  261. {ingestr-0.13.51 → ingestr-0.13.53}/styles/Google/Exclamation.yml +0 -0
  262. {ingestr-0.13.51 → ingestr-0.13.53}/styles/Google/FirstPerson.yml +0 -0
  263. {ingestr-0.13.51 → ingestr-0.13.53}/styles/Google/Gender.yml +0 -0
  264. {ingestr-0.13.51 → ingestr-0.13.53}/styles/Google/GenderBias.yml +0 -0
  265. {ingestr-0.13.51 → ingestr-0.13.53}/styles/Google/HeadingPunctuation.yml +0 -0
  266. {ingestr-0.13.51 → ingestr-0.13.53}/styles/Google/Headings.yml +0 -0
  267. {ingestr-0.13.51 → ingestr-0.13.53}/styles/Google/Latin.yml +0 -0
  268. {ingestr-0.13.51 → ingestr-0.13.53}/styles/Google/LyHyphens.yml +0 -0
  269. {ingestr-0.13.51 → ingestr-0.13.53}/styles/Google/OptionalPlurals.yml +0 -0
  270. {ingestr-0.13.51 → ingestr-0.13.53}/styles/Google/Ordinal.yml +0 -0
  271. {ingestr-0.13.51 → ingestr-0.13.53}/styles/Google/OxfordComma.yml +0 -0
  272. {ingestr-0.13.51 → ingestr-0.13.53}/styles/Google/Parens.yml +0 -0
  273. {ingestr-0.13.51 → ingestr-0.13.53}/styles/Google/Passive.yml +0 -0
  274. {ingestr-0.13.51 → ingestr-0.13.53}/styles/Google/Periods.yml +0 -0
  275. {ingestr-0.13.51 → ingestr-0.13.53}/styles/Google/Quotes.yml +0 -0
  276. {ingestr-0.13.51 → ingestr-0.13.53}/styles/Google/Ranges.yml +0 -0
  277. {ingestr-0.13.51 → ingestr-0.13.53}/styles/Google/Semicolons.yml +0 -0
  278. {ingestr-0.13.51 → ingestr-0.13.53}/styles/Google/Slang.yml +0 -0
  279. {ingestr-0.13.51 → ingestr-0.13.53}/styles/Google/Spacing.yml +0 -0
  280. {ingestr-0.13.51 → ingestr-0.13.53}/styles/Google/Spelling.yml +0 -0
  281. {ingestr-0.13.51 → ingestr-0.13.53}/styles/Google/Units.yml +0 -0
  282. {ingestr-0.13.51 → ingestr-0.13.53}/styles/Google/We.yml +0 -0
  283. {ingestr-0.13.51 → ingestr-0.13.53}/styles/Google/Will.yml +0 -0
  284. {ingestr-0.13.51 → ingestr-0.13.53}/styles/Google/WordList.yml +0 -0
  285. {ingestr-0.13.51 → ingestr-0.13.53}/styles/Google/meta.json +0 -0
  286. {ingestr-0.13.51 → ingestr-0.13.53}/styles/Google/vocab.txt +0 -0
  287. {ingestr-0.13.51 → ingestr-0.13.53}/styles/bruin/Ingestr.yml +0 -0
  288. {ingestr-0.13.51 → ingestr-0.13.53}/styles/config/vocabularies/bruin/accept.txt +0 -0
  289. {ingestr-0.13.51 → ingestr-0.13.53}/test.env.template +0 -0
@@ -3,6 +3,7 @@ __pycache__
3
3
  .env
4
4
  venv
5
5
  !.gitkeep
6
+ .idea
6
7
  .vscode/*
7
8
  .metals/*
8
9
  .coverage.*
@@ -1,6 +1,6 @@
1
1
  Metadata-Version: 2.4
2
2
  Name: ingestr
3
- Version: 0.13.51
3
+ Version: 0.13.53
4
4
  Summary: ingestr is a command-line application that ingests data from various sources and stores them in any database.
5
5
  Project-URL: Homepage, https://github.com/bruin-data/ingestr
6
6
  Project-URL: Issues, https://github.com/bruin-data/ingestr/issues
@@ -26,6 +26,7 @@ Requires-Dist: asn1crypto==1.5.1
26
26
  Requires-Dist: asynch==0.2.4
27
27
  Requires-Dist: attrs==25.1.0
28
28
  Requires-Dist: backoff==2.2.1
29
+ Requires-Dist: bcrypt==4.3.0
29
30
  Requires-Dist: beautifulsoup4==4.13.3
30
31
  Requires-Dist: boto3==1.37.1
31
32
  Requires-Dist: botocore==1.37.1
@@ -39,6 +40,7 @@ Requires-Dist: clickhouse-connect==0.8.14
39
40
  Requires-Dist: clickhouse-driver==0.2.9
40
41
  Requires-Dist: clickhouse-sqlalchemy==0.2.7
41
42
  Requires-Dist: confluent-kafka==2.8.0
43
+ Requires-Dist: crate==2.0.0
42
44
  Requires-Dist: cryptography==44.0.2
43
45
  Requires-Dist: curlify==2.2.1
44
46
  Requires-Dist: databricks-sql-connector==2.9.3
@@ -59,6 +61,7 @@ Requires-Dist: flatten-json==0.1.14
59
61
  Requires-Dist: frozenlist==1.5.0
60
62
  Requires-Dist: fsspec==2025.3.2
61
63
  Requires-Dist: gcsfs==2025.3.2
64
+ Requires-Dist: geojson==3.2.0
62
65
  Requires-Dist: gitdb==4.0.12
63
66
  Requires-Dist: gitpython==3.1.44
64
67
  Requires-Dist: giturlparse==0.12.0
@@ -77,7 +80,7 @@ Requires-Dist: google-cloud-storage==3.1.0
77
80
  Requires-Dist: google-crc32c==1.6.0
78
81
  Requires-Dist: google-resumable-media==2.7.2
79
82
  Requires-Dist: googleapis-common-protos==1.69.0
80
- Requires-Dist: greenlet==3.2.2
83
+ Requires-Dist: greenlet==3.2.3
81
84
  Requires-Dist: grpc-google-iam-v1==0.14.2
82
85
  Requires-Dist: grpc-interceptor==0.15.4
83
86
  Requires-Dist: grpcio-status==1.62.3
@@ -113,6 +116,7 @@ Requires-Dist: openpyxl==3.1.5
113
116
  Requires-Dist: orjson==3.10.15
114
117
  Requires-Dist: packaging==24.2
115
118
  Requires-Dist: pandas==2.2.3
119
+ Requires-Dist: paramiko==3.5.1
116
120
  Requires-Dist: pathvalidate==3.2.3
117
121
  Requires-Dist: pendulum==3.0.0
118
122
  Requires-Dist: platformdirs==4.3.6
@@ -137,6 +141,7 @@ Requires-Dist: pygments==2.19.1
137
141
  Requires-Dist: pyjwt==2.10.1
138
142
  Requires-Dist: pymongo==4.11.1
139
143
  Requires-Dist: pymysql==1.1.1
144
+ Requires-Dist: pynacl==1.5.0
140
145
  Requires-Dist: pyopenssl==25.0.0
141
146
  Requires-Dist: pyparsing==3.2.1
142
147
  Requires-Dist: pyrate-limiter==3.7.0
@@ -170,6 +175,7 @@ Requires-Dist: snowflake-sqlalchemy==1.6.1
170
175
  Requires-Dist: sortedcontainers==2.4.0
171
176
  Requires-Dist: soupsieve==2.6
172
177
  Requires-Dist: sqlalchemy-bigquery==1.12.1
178
+ Requires-Dist: sqlalchemy-cratedb==0.42.0.dev2
173
179
  Requires-Dist: sqlalchemy-hana==2.0.0
174
180
  Requires-Dist: sqlalchemy-redshift==0.8.14
175
181
  Requires-Dist: sqlalchemy-spanner==1.11.0
@@ -192,6 +198,7 @@ Requires-Dist: tzdata==2025.1
192
198
  Requires-Dist: tzlocal==5.3
193
199
  Requires-Dist: uritemplate==4.1.1
194
200
  Requires-Dist: urllib3==2.3.0
201
+ Requires-Dist: verlib2==0.3.1
195
202
  Requires-Dist: wrapt==1.17.2
196
203
  Requires-Dist: yarl==1.18.3
197
204
  Requires-Dist: zeep==4.3.1
@@ -292,11 +299,21 @@ Pull requests are welcome. However, please open an issue first to discuss what y
292
299
  <td>✅</td>
293
300
  <td>✅</td>
294
301
  </tr>
302
+ <tr>
303
+ <td>CrateDB</td>
304
+ <td>✅</td>
305
+ <td>❌</td>
306
+ </tr>
295
307
  <tr>
296
308
  <td>Databricks</td>
297
309
  <td>✅</td>
298
310
  <td>✅</td>
299
311
  </tr>
312
+ <tr>
313
+ <td>IBM Db2</td>
314
+ <td>✅</td>
315
+ <td>-</td>
316
+ </tr>
300
317
  <tr>
301
318
  <td>DuckDB</td>
302
319
  <td>✅</td>
@@ -307,6 +324,16 @@ Pull requests are welcome. However, please open an issue first to discuss what y
307
324
  <td>✅</td>
308
325
  <td>-</td>
309
326
  </tr>
327
+ <tr>
328
+ <td>Elasticsearch</td>
329
+ <td>✅</td>
330
+ <td>-</td>
331
+ </tr>
332
+ <tr>
333
+ <td>GCP Spanner</td>
334
+ <td>✅</td>
335
+ <td>-</td>
336
+ </tr>
310
337
  <tr>
311
338
  <td>Local CSV file</td>
312
339
  <td>✅</td>
@@ -393,6 +420,11 @@ Pull requests are welcome. However, please open an issue first to discuss what y
393
420
  <td>✅</td>
394
421
  <td>-</td>
395
422
  </tr>
423
+ <tr>
424
+ <td>Attio</td>
425
+ <td>✅</td>
426
+ <td>-</td>
427
+ </tr>
396
428
  <tr>
397
429
  <td>Chess.com</td>
398
430
  <td>✅</td>
@@ -404,7 +436,7 @@ Pull requests are welcome. However, please open an issue first to discuss what y
404
436
  <td>-</td>
405
437
  </tr>
406
438
  <tr>
407
- <td>Github</td>
439
+ <td>GitHub</td>
408
440
  <td>✅</td>
409
441
  <td>-</td>
410
442
  </tr>
@@ -447,6 +479,16 @@ Pull requests are welcome. However, please open an issue first to discuss what y
447
479
  <td>Personio</td>
448
480
  <td>✅</td>
449
481
  <td>-</td>
482
+ </tr>
483
+ <tr>
484
+ <td>Phantombuster</td>
485
+ <td>✅</td>
486
+ <td>-</td>
487
+ </tr>
488
+ <tr>
489
+ <td>Pipedrive</td>
490
+ <td>✅</td>
491
+ <td>-</td>
450
492
  </tr>
451
493
  <tr>
452
494
  <td>S3</td>
@@ -469,7 +511,12 @@ Pull requests are welcome. However, please open an issue first to discuss what y
469
511
  <td>-</td>
470
512
  </tr>
471
513
  <tr>
472
- <td>Smartsheet</td>
514
+ <td>Smartsheets</td>
515
+ <td>✅</td>
516
+ <td>-</td>
517
+ </tr>
518
+ <tr>
519
+ <td>Solidgate</td>
473
520
  <td>✅</td>
474
521
  <td>-</td>
475
522
  </tr>
@@ -87,11 +87,21 @@ Pull requests are welcome. However, please open an issue first to discuss what y
87
87
  <td>✅</td>
88
88
  <td>✅</td>
89
89
  </tr>
90
+ <tr>
91
+ <td>CrateDB</td>
92
+ <td>✅</td>
93
+ <td>❌</td>
94
+ </tr>
90
95
  <tr>
91
96
  <td>Databricks</td>
92
97
  <td>✅</td>
93
98
  <td>✅</td>
94
99
  </tr>
100
+ <tr>
101
+ <td>IBM Db2</td>
102
+ <td>✅</td>
103
+ <td>-</td>
104
+ </tr>
95
105
  <tr>
96
106
  <td>DuckDB</td>
97
107
  <td>✅</td>
@@ -102,6 +112,16 @@ Pull requests are welcome. However, please open an issue first to discuss what y
102
112
  <td>✅</td>
103
113
  <td>-</td>
104
114
  </tr>
115
+ <tr>
116
+ <td>Elasticsearch</td>
117
+ <td>✅</td>
118
+ <td>-</td>
119
+ </tr>
120
+ <tr>
121
+ <td>GCP Spanner</td>
122
+ <td>✅</td>
123
+ <td>-</td>
124
+ </tr>
105
125
  <tr>
106
126
  <td>Local CSV file</td>
107
127
  <td>✅</td>
@@ -188,6 +208,11 @@ Pull requests are welcome. However, please open an issue first to discuss what y
188
208
  <td>✅</td>
189
209
  <td>-</td>
190
210
  </tr>
211
+ <tr>
212
+ <td>Attio</td>
213
+ <td>✅</td>
214
+ <td>-</td>
215
+ </tr>
191
216
  <tr>
192
217
  <td>Chess.com</td>
193
218
  <td>✅</td>
@@ -199,7 +224,7 @@ Pull requests are welcome. However, please open an issue first to discuss what y
199
224
  <td>-</td>
200
225
  </tr>
201
226
  <tr>
202
- <td>Github</td>
227
+ <td>GitHub</td>
203
228
  <td>✅</td>
204
229
  <td>-</td>
205
230
  </tr>
@@ -242,6 +267,16 @@ Pull requests are welcome. However, please open an issue first to discuss what y
242
267
  <td>Personio</td>
243
268
  <td>✅</td>
244
269
  <td>-</td>
270
+ </tr>
271
+ <tr>
272
+ <td>Phantombuster</td>
273
+ <td>✅</td>
274
+ <td>-</td>
275
+ </tr>
276
+ <tr>
277
+ <td>Pipedrive</td>
278
+ <td>✅</td>
279
+ <td>-</td>
245
280
  </tr>
246
281
  <tr>
247
282
  <td>S3</td>
@@ -264,7 +299,12 @@ Pull requests are welcome. However, please open an issue first to discuss what y
264
299
  <td>-</td>
265
300
  </tr>
266
301
  <tr>
267
- <td>Smartsheet</td>
302
+ <td>Smartsheets</td>
303
+ <td>✅</td>
304
+ <td>-</td>
305
+ </tr>
306
+ <tr>
307
+ <td>Solidgate</td>
268
308
  <td>✅</td>
269
309
  <td>-</td>
270
310
  </tr>
@@ -136,8 +136,9 @@ export default defineConfig({
136
136
  { text: "Personio", link: "/supported-sources/personio.md" },
137
137
  { text: "PhantomBuster", link: "/supported-sources/phantombuster.md" },
138
138
  { text: "Pipedrive", link: "/supported-sources/pipedrive.md" },
139
- { text: "S3", link: "/supported-sources/s3.md" },
139
+ { text: "S3", link: "/supported-sources/s3.md"},
140
140
  { text: "Salesforce", link: "/supported-sources/salesforce.md" },
141
+ { text: "SFTP", link: "/supported-sources/sftp.md"},
141
142
  { text: "Shopify", link: "/supported-sources/shopify.md" },
142
143
  { text: "Slack", link: "/supported-sources/slack.md" },
143
144
  { text: "Smartsheet", link: "/supported-sources/smartsheets.md" },
Binary file
@@ -0,0 +1,80 @@
1
+ # CrateDB
2
+
3
+ [CrateDB] is a distributed and scalable SQL database for storing and analyzing
4
+ massive amounts of data in near real-time, even with complex queries. It is
5
+ PostgreSQL-compatible, and based on Lucene.
6
+
7
+ ingestr supports CrateDB as a source database.
8
+
9
+ ## Source
10
+
11
+ For connecting to CrateDB as a database source, ingestr uses its SQLAlchemy
12
+ dialect package [sqlalchemy-cratedb].
13
+
14
+ ### URI format
15
+
16
+ The URI format for CrateDB as a source is as follows:
17
+ ```plaintext
18
+ crate://<username>:<password>@<host>:<port>?ssl=<ssl>
19
+ ```
20
+ > [!INFO]
21
+ > The driver does not require any option, and will default to
22
+ > `crate://crate@localhost:4200?ssl=false` when just using `crate://`.
23
+ >
24
+ > When connecting to CrateDB on localhost, use:
25
+ > ```plaintext
26
+ > crate://crate@localhost:4200?ssl=false
27
+ > ```
28
+ >
29
+ > When connecting to [CrateDB Cloud], the URI looks like this:
30
+ > ```plaintext
31
+ > crate://admin:<PASSWORD>@<CLUSTERNAME>.eks1.eu-west-1.aws.cratedb.net:4200?ssl=true
32
+ > ```
33
+
34
+ ### URI parameters
35
+ - `username` (required): The username is required to authenticate with the CrateDB server.
36
+ - `password` (required): The password is required to authenticate the provided username.
37
+ - `host` (required): The hostname or IP address of the CrateDB server where the database is hosted.
38
+ - `port` (required): The TCP port number used by the CrateDB server. Mostly `4200`.
39
+ - `ssl` (optional): Set to `true` for a secure HTTPS connection. By default, SSL is disabled (`false`).
40
+
41
+ ### Example
42
+
43
+ This is an example command that will copy the `sys.summits` table from CrateDB
44
+ to DuckDB, then display the content from DuckDB.
45
+
46
+ ```shell
47
+ ingestr ingest \
48
+ --source-uri 'crate://crate@localhost:4200/' \
49
+ --source-table 'sys.summits' \
50
+ --dest-uri 'duckdb:///cratedb.duckdb' \
51
+ --dest-table 'dest.summits'
52
+ ```
53
+ ```shell
54
+ duckdb cratedb.duckdb 'SELECT * FROM dest.summits LIMIT 5'
55
+ ```
56
+
57
+ <img alt="CrateDB_img" src="../media/cratedb-source.png" />
58
+
59
+
60
+ ## Appendix
61
+
62
+ To start a single-node instance of CrateDB for evaluation purposes,
63
+ use Docker or Podman.
64
+ ```shell
65
+ docker run --rm -it --name=cratedb \
66
+ --publish=4200:4200 --publish=5432:5432 \
67
+ --env=CRATE_HEAP_SIZE=2g crate/crate:nightly \
68
+ -Cdiscovery.type=single-node
69
+ ```
70
+
71
+ We are tracking development progress and incompatibilities at
72
+ [Support for ingestr/CrateDB] and ["tool: dlt/ingestr"]. Please join the discussion
73
+ or share relevant issue reports that help us improve interoperability. Thanks!
74
+
75
+
76
+ [CrateDB]: https://github.com/crate/crate
77
+ [CrateDB Cloud]: https://console.cratedb.cloud/
78
+ [sqlalchemy-cratedb]: https://pypi.org/project/sqlalchemy-cratedb/
79
+ [Support for ingestr/CrateDB]: https://github.com/crate/crate-clients-tools/issues/86
80
+ ["tool: dlt/ingestr"]: https://github.com/crate/crate/issues?q=state%3Aopen%20label%3A%22tool%3A%20dlt%2Fingestr%22
@@ -1,13 +1,13 @@
1
1
  # MySQL
2
2
  MySQL is an open source relational database management system, known for its speed and reliability.
3
3
 
4
- ingestr supports MySQL as a source.
4
+ ingestr supports MySQL as a source and a destination.
5
5
 
6
6
  ## URI format
7
7
  The URI format for MySQL is as follows:
8
8
 
9
9
  ```plaintext
10
- mysql://user:password@host:port/dbname
10
+ mysql://user:password@host:port/dbname
11
11
  ```
12
12
 
13
13
  URI parameters:
@@ -17,4 +17,4 @@ URI parameters:
17
17
  - `port`: the port number the database server is listening on, the default is 3306
18
18
  - `dbname`: the name of the database to connect to
19
19
 
20
- The same URI structure can be used both for sources and destinations. You can read more about SQLAlchemy's MySQL dialect [here](https://docs.sqlalchemy.org/en/20/core/engines.html#mysql).
20
+ The same URI structure and table can be used both for sources and destinations. You can read more about SQLAlchemy's MySQL dialect [here](https://docs.sqlalchemy.org/en/20/core/engines.html#mysql).
@@ -0,0 +1,43 @@
1
+ # SFTP
2
+
3
+ SFTP (SSH File Transfer Protocol) is a secure file transfer protocol that runs over the SSH protocol. It provides a secure way to transfer files between a local and a remote computer.
4
+
5
+ `ingestr` supports SFTP as a data source.
6
+
7
+ ## URI Format
8
+
9
+ The URI for connecting to an SFTP server is structured as follows:
10
+
11
+ ```plaintext
12
+ sftp://<username>:<password>@<host>:<port>
13
+ ```
14
+
15
+ ## URI Components:
16
+ - `username`: The username for the SFTP server.
17
+ - `password`: The password for the SFTP server.
18
+ - `host`: The hostname or IP address of the SFTP server.
19
+ - `port`: The port number of the SFTP server (defaults to 22 if not specified).
20
+
21
+ ## Setting up an SFTP Integration
22
+
23
+ To integrate `ingestr` with an SFTP server, you need the server's hostname, port, a valid username, and a password.
24
+
25
+ Once you have your credentials, you can load data to desired destaination.
26
+
27
+ ### Example: Loading data from SFTP TO DUCKDB
28
+
29
+ ```sh
30
+ ingestr ingest \
31
+ --source-uri 'sftp://myuser:MySecretPassword123@sftp.example.com' \
32
+ --source-table 'user.csv' \
33
+ --dest-uri duckdb:///sftp_data.duckdb \
34
+ --dest-table 'dest.users_deatils'
35
+ ```
36
+
37
+ <img alt="sftp" src="../media/sftp.png"/>
38
+
39
+
40
+ The `--source-table` specifies `/path/to/directory` The base directory on the server where `ingestr` should start looking for files.
41
+
42
+
43
+
@@ -39,8 +39,9 @@ The result of this command will be a table in the `Solidgate.duckdb` database wi
39
39
 
40
40
  Solidgate source allows ingesting the following sources into separate tables:
41
41
  - `subscriptions`: Provides a comprehensive view of customer subscriptions, including subscription IDs, statuses, and key timestamps such as creation, update, and expiration dates.
42
- - `apm-orders`: Provides essential information for anti-fraud purposes, including order IDs, transaction statuses, amounts, currencies, and payment methods, along with crucial customer details such as email addresses.
43
- - `card-orders`: Provides detailed information on orders processed via card payments, including transaction data, payment status, and customer details.
42
+ - `apm_orders`: Provides essential information for anti-fraud purposes, including order IDs, transaction statuses, amounts, currencies, and payment methods, along with crucial customer details such as email addresses.
43
+ - `card_orders`: Provides detailed information on orders processed via card payments, including transaction data, payment status, and customer details.
44
+ - `financial_entries`: Provides a detailed transaction-level breakdown of financial records.
44
45
 
45
46
  Use these as `--source-table` parameter in the `ingestr ingest` command.
46
47
 
@@ -1,7 +1,7 @@
1
1
  # SQLite
2
2
  SQLite is a C-language library that implements a small, fast, self-contained, high-reliability, full-featured, SQL database engine.
3
3
 
4
- ingestr supports SQLite as a source.
4
+ ingestr supports SQLite as a source and a destination.
5
5
 
6
6
  ## URI format
7
7
  The URI format for SQLite is as follows:
@@ -58,6 +58,7 @@ class LoaderFileFormat(str, Enum):
58
58
 
59
59
 
60
60
  class SqlBackend(str, Enum):
61
+ default = "default"
61
62
  sqlalchemy = "sqlalchemy"
62
63
  pyarrow = "pyarrow"
63
64
  connectorx = "connectorx"
@@ -187,7 +188,7 @@ def ingest(
187
188
  help="The SQL backend to use",
188
189
  envvar=["SQL_BACKEND", "INGESTR_SQL_BACKEND"],
189
190
  ),
190
- ] = SqlBackend.pyarrow, # type: ignore
191
+ ] = SqlBackend.default, # type: ignore
191
192
  loader_file_format: Annotated[
192
193
  Optional[LoaderFileFormat],
193
194
  typer.Option(
@@ -289,7 +290,11 @@ def ingest(
289
290
  from ingestr.src.collector.spinner import SpinnerCollector
290
291
  from ingestr.src.destinations import AthenaDestination
291
292
  from ingestr.src.factory import SourceDestinationFactory
292
- from ingestr.src.filters import cast_set_to_list, handle_mysql_empty_dates
293
+ from ingestr.src.filters import (
294
+ cast_set_to_list,
295
+ cast_spanner_types,
296
+ handle_mysql_empty_dates,
297
+ )
293
298
  from ingestr.src.sources import MongoDbSource
294
299
 
295
300
  def report_errors(run_info: LoadInfo):
@@ -517,6 +522,15 @@ def ingest(
517
522
  if interval_end:
518
523
  interval_end = interval_end.date() # type: ignore
519
524
 
525
+ if factory.source_scheme.startswith("spanner"):
526
+ # we tend to use the 'pyarrow' backend in general, however, it has issues with JSON objects, so we override it to 'sqlalchemy' for Spanner.
527
+ if sql_backend.value == SqlBackend.default:
528
+ sql_backend = SqlBackend.sqlalchemy
529
+
530
+ # this allows us to identify the cases where the user does not have a preference, so that for some sources we can override it.
531
+ if sql_backend == SqlBackend.default:
532
+ sql_backend = SqlBackend.pyarrow
533
+
520
534
  dlt_source = source.dlt_source(
521
535
  uri=source_uri,
522
536
  table=source_table,
@@ -535,6 +549,9 @@ def ingest(
535
549
  if factory.source_scheme.startswith("mysql"):
536
550
  resource.for_each(dlt_source, lambda x: x.add_map(handle_mysql_empty_dates))
537
551
 
552
+ if factory.source_scheme.startswith("spanner"):
553
+ resource.for_each(dlt_source, lambda x: x.add_map(cast_spanner_types))
554
+
538
555
  if yield_limit:
539
556
  resource.for_each(dlt_source, lambda x: x.add_limit(yield_limit))
540
557
 
@@ -0,0 +1 @@
1
+ version = "v0.13.53"
@@ -468,3 +468,33 @@ class S3Destination:
468
468
 
469
469
  def post_load(self) -> None:
470
470
  pass
471
+
472
+
473
+ class SqliteDestination(GenericSqlDestination):
474
+ def dlt_dest(self, uri: str, **kwargs):
475
+ return dlt.destinations.sqlalchemy(credentials=uri)
476
+
477
+ def dlt_run_params(self, uri: str, table: str, **kwargs):
478
+ return {
479
+ #https://dlthub.com/docs/dlt-ecosystem/destinations/sqlalchemy#dataset-files
480
+ "dataset_name": "main",
481
+ "table_name": table,
482
+ }
483
+
484
+
485
+ class MySqlDestination(GenericSqlDestination):
486
+ def dlt_dest(self, uri: str, **kwargs):
487
+ return dlt.destinations.sqlalchemy(credentials=uri)
488
+
489
+ def dlt_run_params(self, uri: str, table: str, **kwargs):
490
+ parsed = urlparse(uri)
491
+ database = parsed.path.lstrip("/")
492
+ if not database:
493
+ raise ValueError("You need to specify a database")
494
+ return {
495
+ "dataset_name": database,
496
+ "table_name": table,
497
+ }
498
+
499
+
500
+
@@ -11,10 +11,12 @@ from ingestr.src.destinations import (
11
11
  DatabricksDestination,
12
12
  DuckDBDestination,
13
13
  MsSQLDestination,
14
+ MySqlDestination,
14
15
  PostgresDestination,
15
16
  RedshiftDestination,
16
17
  S3Destination,
17
18
  SnowflakeDestination,
19
+ SqliteDestination,
18
20
  SynapseDestination,
19
21
  )
20
22
  from ingestr.src.sources import (
@@ -52,18 +54,20 @@ from ingestr.src.sources import (
52
54
  PipedriveSource,
53
55
  S3Source,
54
56
  SalesforceSource,
57
+ SFTPSource,
55
58
  ShopifySource,
56
59
  SlackSource,
60
+ SmartsheetSource,
57
61
  SolidgateSource,
58
62
  SqlSource,
59
63
  StripeAnalyticsSource,
60
64
  TikTokSource,
61
65
  ZendeskSource,
62
- SmartsheetSource,
63
66
  )
64
67
 
65
68
  SQL_SOURCE_SCHEMES = [
66
69
  "bigquery",
70
+ "crate",
67
71
  "duckdb",
68
72
  "mssql",
69
73
  "mysql",
@@ -163,6 +167,7 @@ class SourceDestinationFactory:
163
167
  "attio": AttioSource,
164
168
  "solidgate": SolidgateSource,
165
169
  "smartsheet": SmartsheetSource,
170
+ "sftp": SFTPSource,
166
171
  }
167
172
  destinations: Dict[str, Type[DestinationProtocol]] = {
168
173
  "bigquery": BigQueryDestination,
@@ -182,6 +187,9 @@ class SourceDestinationFactory:
182
187
  "clickhouse+native": ClickhouseDestination,
183
188
  "clickhouse": ClickhouseDestination,
184
189
  "s3": S3Destination,
190
+ "sqlite": SqliteDestination,
191
+ "mysql": MySqlDestination,
192
+ "mysql+pymysql": MySqlDestination,
185
193
  }
186
194
 
187
195
  def __init__(self, source_uri: str, destination_uri: str):
@@ -7,6 +7,20 @@ def cast_set_to_list(row):
7
7
  return row
8
8
 
9
9
 
10
+ def cast_spanner_types(row):
11
+ if not isinstance(row, dict):
12
+ return row
13
+
14
+ from google.cloud.spanner_v1.data_types import JsonObject
15
+
16
+ for key in row.keys():
17
+ if isinstance(row[key], JsonObject):
18
+ import json
19
+
20
+ row[key] = json.loads(row[key].serialize())
21
+ return row
22
+
23
+
10
24
  def handle_mysql_empty_dates(row):
11
25
  # MySQL returns empty dates as 0000-00-00, which is not a valid date, we handle them here.
12
26
  if not isinstance(row, dict):
@@ -43,7 +43,7 @@ def solidgate_source(
43
43
  yield solidgate_client.fetch_data(path, date_from=start_dt, date_to=end_dt)
44
44
 
45
45
  @dlt.resource(
46
- name="apm-orders",
46
+ name="apm_orders",
47
47
  write_disposition="merge",
48
48
  primary_key="order_id",
49
49
  columns={
@@ -69,7 +69,7 @@ def solidgate_source(
69
69
  yield solidgate_client.fetch_data(path, date_from=start_dt, date_to=end_dt)
70
70
 
71
71
  @dlt.resource(
72
- name="card-orders",
72
+ name="card_orders",
73
73
  write_disposition="merge",
74
74
  primary_key="order_id",
75
75
  columns={
@@ -95,7 +95,7 @@ def solidgate_source(
95
95
  yield solidgate_client.fetch_data(path, date_from=start_dt, date_to=end_dt)
96
96
 
97
97
  @dlt.resource(
98
- name="financial-entries",
98
+ name="financial_entries",
99
99
  write_disposition="merge",
100
100
  primary_key="id",
101
101
  columns={