fix: rename sd-data-ingest → oceanstream-cli in all references

The actual GitHub repo is OceanStreamIO/oceanstream-cli.
sd-data-ingest was the old local folder name.

Author: beatfactor

.github/copilot-instructions.md

@@ -30,9 +30,9 @@ Sensor data (TCP/UDP stream, file drop, IoT Edge message)
 
 ### Oceanstream Dependency
 
-All data parsing is handled by the **oceanstream** library (`oceanstream` package from `sd-data-ingest` repo). Sensorstream installs it with `[geotrack,adcp]` extras:
+All data parsing is handled by the **oceanstream** library (`oceanstream` package from `oceanstream-cli` repo). Sensorstream installs it with `[geotrack,adcp]` extras:
 
-- **Local dev**: `pip install -e "../sd-data-ingest[geotrack,adcp]"`
+- **Local dev**: `pip install -e "../oceanstream-cli[geotrack,adcp]"`
 - **Production**: `pip install "oceanstream[geotrack,adcp] @ git+https://github.com/OceanStreamIO/oceanstream-cli.git"`
 
 The adapter (`ingest/adapter.py`) provides:
@@ -138,7 +138,7 @@ The `test/conftest.py` session fixtures automatically:
 2. Use size-based freshness checks on subsequent runs
 3. Fall back to local `test_data/` if no Azure connection
 
-**Connection string**: Set `AZURE_CONNECTION_STRING` in `.env` or environment. The conftest also checks `../sd-data-ingest/.env`.
+**Connection string**: Set `AZURE_CONNECTION_STRING` in `.env` or environment. The conftest also checks `../oceanstream-cli/.env`.
 
 Key fixtures (all session-scoped):
 - `test_data_dir` — root of synced test data

Dockerfile.Linux.amd64

@@ -9,7 +9,7 @@ RUN apt-get update && apt-get install -y --no-install-recommends \
 
 # Install oceanstream from git
 ARG OCEANSTREAM_BRANCH=main
-ARG OCEANSTREAM_REPO=https://github.com/OceanStreamIO/sd-data-ingest.git
+ARG OCEANSTREAM_REPO=https://github.com/OceanStreamIO/oceanstream-cli.git
 RUN git clone --depth 1 -b ${OCEANSTREAM_BRANCH} ${OCEANSTREAM_REPO} /tmp/oceanstream && \
     pip install --no-cache-dir "/tmp/oceanstream[geotrack,adcp]" && \
     rm -rf /tmp/oceanstream

Dockerfile.Linux.arm64

@@ -9,7 +9,7 @@ RUN apt-get update && apt-get install -y --no-install-recommends \
 
 # Install oceanstream from git
 ARG OCEANSTREAM_BRANCH=main
-ARG OCEANSTREAM_REPO=https://github.com/OceanStreamIO/sd-data-ingest.git
+ARG OCEANSTREAM_REPO=https://github.com/OceanStreamIO/oceanstream-cli.git
 RUN git clone --depth 1 -b ${OCEANSTREAM_BRANCH} ${OCEANSTREAM_REPO} /tmp/oceanstream && \
     pip install --no-cache-dir "/tmp/oceanstream[geotrack,adcp]" && \
     rm -rf /tmp/oceanstream

requirements.txt

@@ -16,6 +16,6 @@ python-dotenv
 psutil
 
 # Oceanstream library (provides all parsing: NMEA, CSV, CTD hex, ADCP)
-# For local development, install with: pip install -e ../sd-data-ingest[geotrack,adcp]
+# For local development, install with: pip install -e ../oceanstream-cli[geotrack,adcp]
 # For production, install from git:
 # pip install "oceanstream[geotrack,adcp] @ git+https://github.com/OceanStreamIO/oceanstream-cli.git"

simulate/file_simulator.py

@@ -7,12 +7,12 @@
 Usage::
 
     python -m simulate.file_simulator \\
-        --source-dir ../sd-data-ingest/raw_data/emso \\
+        --source-dir ../oceanstream-cli/raw_data/emso \\
         --target-dir /tmp/sensorstream-watch \\
         --interval 10
 
     python -m simulate.file_simulator \\
-        --source-dir ../sd-data-ingest/raw_data/r2r \\
+        --source-dir ../oceanstream-cli/raw_data/r2r \\
         --target-dir /tmp/sensorstream-watch \\
         --interval 5 --loop
 """

simulate/stream_simulator.py

@@ -6,11 +6,11 @@
 Usage::
 
     python -m simulate.stream_simulator \\
-        --file ../sd-data-ingest/raw_data/r2r/RR2401_gnss_gp170_aft-2024-02-17.txt \\
+        --file ../oceanstream-cli/raw_data/r2r/RR2401_gnss_gp170_aft-2024-02-17.txt \\
         --protocol tcp --port 9100 --rate 10 --loop
 
     python -m simulate.stream_simulator \\
-        --file ../sd-data-ingest/raw_data/emso/EMSO_OBSEA_CTD_30min.csv \\
+        --file ../oceanstream-cli/raw_data/emso/EMSO_OBSEA_CTD_30min.csv \\
         --protocol udp --port 9100 --format csv --rate 5
 """
 

standalone.py

@@ -8,7 +8,7 @@
 
     # Process files from a directory
     python standalone.py \\
-        --input-dir ../sd-data-ingest/raw_data/emso \\
+        --input-dir ../oceanstream-cli/raw_data/emso \\
         --output-dir ./output \\
         --campaign-id EMSO_test \\
         --provider emso
@@ -27,7 +27,7 @@
 
     # Run with built-in stream simulator
     python standalone.py \\
-        --simulate-stream ../sd-data-ingest/raw_data/r2r/RR2401_gnss_gp170_aft-2024-02-17.txt \\
+        --simulate-stream ../oceanstream-cli/raw_data/r2r/RR2401_gnss_gp170_aft-2024-02-17.txt \\
         --output-dir ./output \\
         --campaign-id R2R_test
 """

test/conftest.py

@@ -13,7 +13,7 @@
 -----------
 AZURE_CONNECTION_STRING : str
     Connection string for the ``ne1osvmdevtest`` storage account.
-    Loaded from ``../sd-data-ingest/.env`` or the local ``.env``.
+    Loaded from ``../oceanstream-cli/.env`` or the local ``.env``.
 SENSORSTREAM_TEST_CONTAINER : str
     Container name (default ``sensorstream-test``).
 SENSORSTREAM_TEST_CACHE : str
@@ -41,7 +41,7 @@
 # Try multiple .env locations
 for _env in [
     Path(__file__).resolve().parent.parent / ".env",
-    Path(__file__).resolve().parent.parent.parent / "sd-data-ingest" / ".env",
+    Path(__file__).resolve().parent.parent.parent / "oceanstream-cli" / ".env",
 ]:
     if _env.exists():
         load_dotenv(_env)

test/generate_test_data.py

@@ -192,19 +192,19 @@ def main():
 
     # Copy the original EMSO for comparison
     import shutil
-    src = Path(__file__).parent.parent / "sd-data-ingest" / "raw_data" / "emso" / "EMSO_OBSEA_CTD_30min.csv"
+    src = Path(__file__).parent.parent / "oceanstream-cli" / "raw_data" / "emso" / "EMSO_OBSEA_CTD_30min.csv"
     if src.exists():
         shutil.copy2(src, output_dir / "ctd" / "EMSO_OBSEA_CTD_30min.csv")
         print(f"Copied original EMSO CSV → {output_dir / 'ctd' / 'EMSO_OBSEA_CTD_30min.csv'}")
 
     # Copy processed R2R CNV for testing
-    cnv_src = Path(__file__).parent.parent / "sd-data-ingest" / "raw_data" / "r2r" / "RR2205_ctd_validation" / "processed" / "11901_1db.cnv"
+    cnv_src = Path(__file__).parent.parent / "oceanstream-cli" / "raw_data" / "r2r" / "RR2205_ctd_validation" / "processed" / "11901_1db.cnv"
     if cnv_src.exists():
         shutil.copy2(cnv_src, output_dir / "ctd" / "RR2205_11901_1db.cnv")
         print(f"Copied R2R CNV → {output_dir / 'ctd' / 'RR2205_11901_1db.cnv'}")
 
     # Take a 1000-line slice of the GNSS file for a smaller test
-    gnss_src = Path(__file__).parent.parent / "sd-data-ingest" / "raw_data" / "r2r" / "RR2401_gnss_gp170_aft-2024-02-17.txt"
+    gnss_src = Path(__file__).parent.parent / "oceanstream-cli" / "raw_data" / "r2r" / "RR2401_gnss_gp170_aft-2024-02-17.txt"
     if gnss_src.exists():
         with open(gnss_src) as f:
             lines = [next(f) for _ in range(2000)]

test/test_azure_e2e.py

@@ -27,8 +27,8 @@
 
 from dotenv import load_dotenv
 
-# Load .env from the sd-data-ingest project (where the connection string is)
-_env_path = Path(__file__).resolve().parent.parent.parent / "sd-data-ingest" / ".env"
+# Load .env from the oceanstream-cli project (where the connection string is)
+_env_path = Path(__file__).resolve().parent.parent.parent / "oceanstream-cli" / ".env"
 if _env_path.exists():
     load_dotenv(_env_path)
 # Also try local .env