pybgpkitstream 0.1.0__tar.gz → 0.1.2__tar.gz

{pybgpkitstream-0.1.0 → pybgpkitstream-0.1.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: pybgpkitstream
-Version: 0.1.0
+Version: 0.1.2
 Summary: Drop-in replacement for PyBGPStream using BGPKIT
 Author: JustinLoye
 Author-email: JustinLoye <jloye@iij.ad.jp>
@@ -16,17 +16,25 @@ A drop-in replacement for PyBGPStream using BGPKIT
 
 ## Features
 
-- Effortlessly switch to another BGP stream:
-  - Designed to be a seamless, drop-in replacement ([example](tests/test_stream.py#L38))
+- Effortless BGP Stream Switching:
+  - Seamless, drop-in replacement ([example](tests/test_stream.py#L38))
   - Lazy message generation: generates time-ordered BGP messages on the fly, consuming minimal memory and making it suitable for large datasets
   - Supports multiple route collectors
   - Supports both ribs and updates
-- Caching with concurrent downloading is enabled, and the caching mechanism is fully compatible with the BGPKIT parser's caching functionality
-- [Good-enough performances](examples/perf.ipynb)
+- Caching with concurrent downloading is enabled and is fully compatible with the BGPKIT parser's caching functionality.
+- [Similar performance to PyBGPStream](examples/perf.ipynb)
 - A CLI tool
 
 ## Quick start
 
+Installation:
+
+```sh
+pip install pybgpkitstream
+```
+
+Usage:
+
 ```python
 import datetime
 from pybgpkitstream import BGPStreamConfig, BGPKITStream
@@ -47,6 +55,12 @@ for _ in stream:
 print(f"Processed {n_elems} BGP elements")
 ```
 
+or in the terminal:
+
+```sh
+pybgpkitstream --start-time 2010-09-01T00:00:00 --end-time 2010-09-01T01:59:00 --collectors route-views.sydney route-views.wide --data-types updates > updates.txt
+```
+
 ## Motivation
 
 PyBGPStream is great but the implementation is complex and stops working when UC San Diego experiences a power outage.

{pybgpkitstream-0.1.0 → pybgpkitstream-0.1.2}/README.md

@@ -4,17 +4,25 @@ A drop-in replacement for PyBGPStream using BGPKIT
 
 ## Features
 
-- Effortlessly switch to another BGP stream:
-  - Designed to be a seamless, drop-in replacement ([example](tests/test_stream.py#L38))
+- Effortless BGP Stream Switching:
+  - Seamless, drop-in replacement ([example](tests/test_stream.py#L38))
   - Lazy message generation: generates time-ordered BGP messages on the fly, consuming minimal memory and making it suitable for large datasets
   - Supports multiple route collectors
   - Supports both ribs and updates
-- Caching with concurrent downloading is enabled, and the caching mechanism is fully compatible with the BGPKIT parser's caching functionality
-- [Good-enough performances](examples/perf.ipynb)
+- Caching with concurrent downloading is enabled and is fully compatible with the BGPKIT parser's caching functionality.
+- [Similar performance to PyBGPStream](examples/perf.ipynb)
 - A CLI tool
 
 ## Quick start
 
+Installation:
+
+```sh
+pip install pybgpkitstream
+```
+
+Usage:
+
 ```python
 import datetime
 from pybgpkitstream import BGPStreamConfig, BGPKITStream
@@ -35,6 +43,12 @@ for _ in stream:
 print(f"Processed {n_elems} BGP elements")
 ```
 
+or in the terminal:
+
+```sh
+pybgpkitstream --start-time 2010-09-01T00:00:00 --end-time 2010-09-01T01:59:00 --collectors route-views.sydney route-views.wide --data-types updates > updates.txt
+```
+
 ## Motivation
 
 PyBGPStream is great but the implementation is complex and stops working when UC San Diego experiences a power outage.

{pybgpkitstream-0.1.0 → pybgpkitstream-0.1.2}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "pybgpkitstream"
-version = "0.1.0"
+version = "0.1.2"
 description = "Drop-in replacement for PyBGPStream using BGPKIT"
 readme = "README.md"
 authors = [

{pybgpkitstream-0.1.0 → pybgpkitstream-0.1.2}/src/pybgpkitstream/bgpkitstream.py

@@ -53,6 +53,7 @@ class BGPKITStream:
         data_type: list[Literal["update", "rib"]],
         cache_dir: str | None,
         filters: dict = {},
+        max_concurrent_downloads: int = 10,
     ):
         self.ts_start = ts_start
         self.ts_end = ts_end
@@ -60,6 +61,7 @@ class BGPKITStream:
         self.data_type = data_type
         self.cache_dir = cache_dir
         self.filters = filters
+        self.max_concurrent_downloads = max_concurrent_downloads
 
         self.broker = bgpkit.Broker()
 
@@ -129,8 +131,7 @@ class BGPKITStream:
         self.paths = {"rib": defaultdict(list), "update": defaultdict(list)}
         tasks = []
 
-        CONCURRENT_DOWNLOADS = 10
-        semaphore = asyncio.Semaphore(CONCURRENT_DOWNLOADS)
+        semaphore = asyncio.Semaphore(self.max_concurrent_downloads)
 
         conn = aiohttp.TCPConnector()
         async with aiohttp.ClientSession(connector=conn) as session:
@@ -154,7 +155,7 @@ class BGPKITStream:
 
             if tasks:
                 logging.info(
-                    f"Starting download of {len(tasks)} files with a concurrency of {CONCURRENT_DOWNLOADS}..."
+                    f"Starting download of {len(tasks)} files with a concurrency of {self.max_concurrent_downloads}..."
                 )
                 results = await asyncio.gather(*tasks)
 
@@ -225,4 +226,7 @@ class BGPKITStream:
             filters=config.filters.model_dump(exclude_unset=True)
             if config.filters
             else {},
+            max_concurrent_downloads=config.max_concurrent_downloads
+            if config.max_concurrent_downloads
+            else 10,
         )

{pybgpkitstream-0.1.0 → pybgpkitstream-0.1.2}/src/pybgpkitstream/bgpstreamconfig.py

@@ -40,6 +40,9 @@ class FilterOptions(BaseModel):
     as_path: str | None = Field(
         default=None, description="Filter by a regular expression matching the AS path."
     )
+    ip_version: Literal["ipv4", "ipv6"] | None = Field(
+        default=None, description="Filter by ip version."
+    )
 
 
 class BGPStreamConfig(BaseModel):
@@ -60,3 +63,4 @@ class BGPStreamConfig(BaseModel):
         description="Specifies the directory for caching downloaded files.",
     )
     filters: FilterOptions | None = Field(default=None, description="Optional filters")
+    max_concurrent_downloads: int | None = Field(default=None, description="Maximum concurrent downloads when caching")