Merge centroids into main

docs/networks.md

@@ -131,7 +131,8 @@ All properties preceded by `ML_` will be copied, without that prefix, to the man
 The following are controlled by parameters which can be set using WranglerConfig:
 
 Geometry of managed lanes will be defined as a shape offset by the parameter `ML_OFFSET_METERS`.
-Properties defined in the parameter `ADDITIONAL_COPY_FROM_GP_TO_ML` are also copied from the parent link.
+Link properties defined in the parameter `ADDITIONAL_COPY_FROM_GP_LINK_TO_ML` are also copied from the parent link.
+Node properties defined in the parameter `ADDITIONAL_COPY_FROM_GP_NODE_TO_ML` are copied from the general purpose nodes to the managed lane nodes.
 
 New `model_node_id` s and `model_link_ids` are generated based either on ranges or using a scalar from the GP link based on: `ML_LINK_ID_METHOD`, `ML_NODE_ID_METHOD`, `ML_LINK_ID_RANGE`, `ML_NODE_ID_RANGE`, `ML_LINK_ID_SCALAR`, `ML_NODE_ID_SCALAR`
 

network_wrangler/configs/wrangler.py

@@ -51,7 +51,8 @@
         OVERWRITE_SCOPED: conflicting
     MODEL_ROADWAY:
         ML_OFFSET_METERS: int = -10
-        ADDITIONAL_COPY_FROM_GP_TO_ML: []
+        ADDITIONAL_COPY_FROM_GP_LINK_TO_ML: []
+        ADDITIONAL_COPY_FROM_GP_NODE_TO_ML: []
         ADDITIONAL_COPY_TO_ACCESS_EGRESS: []
     CPU:
         EST_PD_READ_SPEED:
@@ -101,6 +102,7 @@
 
 """
 
+from dataclasses import field
 from typing import Literal
 
 from pydantic import Field
@@ -178,16 +180,62 @@ class ModelRoadwayConfig(ConfigItem):
 
     Attributes:
         ML_OFFSET_METERS: Offset in meters for managed lanes.
-        ADDITIONAL_COPY_FROM_GP_TO_ML: Additional fields to copy from general purpose to managed
-            lanes.
+        ADDITIONAL_COPY_FROM_GP_LINK_TO_ML: Additional link fields to copy from general purpose
+            to managed lanes.
+        ADDITIONAL_COPY_FROM_GP_NODE_TO_ML: Additional node fields to copy from general purpose
+            to managed lane nodes.
         ADDITIONAL_COPY_TO_ACCESS_EGRESS: Additional fields to copy to access and egress links.
     """
 
     ML_OFFSET_METERS: int = -10
-    ADDITIONAL_COPY_FROM_GP_TO_ML: list[str] = Field(default_factory=list)
+    ADDITIONAL_COPY_FROM_GP_LINK_TO_ML: list[str] = Field(default_factory=list)
+    ADDITIONAL_COPY_FROM_GP_NODE_TO_ML: list[str] = Field(default_factory=list)
     ADDITIONAL_COPY_TO_ACCESS_EGRESS: list[str] = Field(default_factory=list)
 
 
+@dataclass
+class TransitConfig(ConfigItem):
+    """Transit Configuration.
+
+    Attributes:
+        K_NEAREST_CANDIDATES: Number of nearest candidate nodes to consider in stop matching
+            when using name scoring. Used in
+            [`match_bus_stops_to_roadway_nodes()`][network_wrangler.utils.transit.match_bus_stops_to_roadway_nodes].
+        NAME_MATCH_WEIGHT: Weight for name match score in combined scoring. 0.9 means 90% name
+            match, 10% distance. Used in
+            [`match_bus_stops_to_roadway_nodes()`][network_wrangler.utils.transit.match_bus_stops_to_roadway_nodes].
+        MIN_SUBSTRING_MATCH_LENGTH: Minimum string length required for substring matching.
+            Prevents spurious matches with single letters. Used in
+            [`assess_stop_name_roadway_compatibility()`][network_wrangler.utils.transit.assess_stop_name_roadway_compatibility].
+        SHAPE_DISTANCE_TOLERANCE: Maximum ratio of path distance to shortest distance in
+            shape-aware routing. 1.10 means paths up to 110% of shortest distance are considered.
+            Used in [`route_shapes_between_stops()`][network_wrangler.utils.transit.route_shapes_between_stops]
+            and [`find_shape_aware_shortest_path()`][network_wrangler.utils.transit.find_shape_aware_shortest_path].
+        MAX_SHAPE_CANDIDATE_PATHS: Maximum number of candidate paths to evaluate when doing
+            shape-aware routing. Used in
+            [`find_shape_aware_shortest_path()`][network_wrangler.utils.transit.find_shape_aware_shortest_path].
+        NEAREST_K_SHAPES_TO_STOPS: Number of nearest shape points to check for each stop.
+        FIRST_LAST_SHAPE_STOP_IDX: For loops, the first stop must match one of the first
+            FIRST_LAST_SHAPE_STOP_IDX shapes, and the last stop must match one of the last
+            FIRST_LAST_SHAPE_STOP_IDX shapes. Used in
+            [`route_shapes_between_stops()`][network_wrangler.utils.transit.route_shapes_between_stops].
+        MAX_DISTANCE_STOP_FEET: Maximum distance in feet for a stop to match to a node.
+            Used in [`match_bus_stops_to_roadway_nodes()`][network_wrangler.utils.transit.match_bus_stops_to_roadway_nodes].
+        MAX_DISTANCE_STOP_METERS: Maximum distance in meters for a stop to match to a node.
+            Used in [`match_bus_stops_to_roadway_nodes()`][network_wrangler.utils.transit.match_bus_stops_to_roadway_nodes].
+    """
+
+    K_NEAREST_CANDIDATES: int = 20
+    NAME_MATCH_WEIGHT: float = 0.9
+    MIN_SUBSTRING_MATCH_LENGTH: int = 3
+    SHAPE_DISTANCE_TOLERANCE: float = 1.10
+    MAX_SHAPE_CANDIDATE_PATHS: int = 20
+    NEAREST_K_SHAPES_TO_STOPS: int = 20
+    FIRST_LAST_SHAPE_STOP_IDX: int = 10
+    MAX_DISTANCE_STOP_FEET: float = 528.0  # 0.10 * 5280 FEET_PER_MILE
+    MAX_DISTANCE_STOP_METERS: float = 150.0  # 0.15 * 1000 METERS_PER_KILOMETER
+
+
 @dataclass
 class CpuConfig(ConfigItem):
     """CPU Configuration -  Will not change any outcomes.
@@ -214,14 +262,16 @@ class WranglerConfig(ConfigItem):
     Attributes:
         IDS: Parameteters governing how new ids are generated.
         MODEL_ROADWAY: Parameters governing how the model roadway is created.
+        TRANSIT: Parameters governing transit network processing.
         CPU: Parameters for accessing CPU information. Will not change any outcomes.
         EDITS: Parameters governing how edits are handled.
     """
 
-    IDS: IdGenerationConfig = IdGenerationConfig()
-    MODEL_ROADWAY: ModelRoadwayConfig = ModelRoadwayConfig()
-    CPU: CpuConfig = CpuConfig()
-    EDITS: EditsConfig = EditsConfig()
+    IDS: IdGenerationConfig = field(default_factory=IdGenerationConfig)
+    MODEL_ROADWAY: ModelRoadwayConfig = field(default_factory=ModelRoadwayConfig)
+    TRANSIT: TransitConfig = field(default_factory=TransitConfig)
+    CPU: CpuConfig = field(default_factory=CpuConfig)
+    EDITS: EditsConfig = field(default_factory=EditsConfig)
 
 
 DefaultConfig = WranglerConfig()

network_wrangler/logger.py

@@ -10,6 +10,50 @@
 WranglerLogger = logging.getLogger("WranglerLogger")
 
 
+class SafeFileHandler(logging.FileHandler):
+    """FileHandler that safely handles flush errors on Windows.
+
+    On Windows, Python's logging can encounter OSError: [Errno 22] Invalid argument
+    when flushing log files due to:
+    - Rapid consecutive writes overwhelming Windows file handle buffering
+    - Large log files causing buffer flush issues
+    - Windows-specific file handle limitations in console/terminal environments
+
+    This handler catches and ignores flush errors while periodically logging
+    that they're occurring to alert users without spamming the error output.
+
+    See: https://bugs.python.org/issue13415 and related Windows logging issues
+    """
+
+    def __init__(self, *args, **kwargs):
+        super().__init__(*args, **kwargs)
+        self._flush_error_count = 0
+        self._last_reported_error_count = 0
+
+    def flush(self):
+        """Flush with error handling for Windows OSError issues.
+
+        Catches OSError during flush operations (common on Windows) and tracks
+        how many times this occurs. Reports every 1000th error to alert users
+        without being too noisy.
+        """
+        try:
+            super().flush()
+        except OSError as e:
+            # Windows-specific flush errors - track but don't crash
+            self._flush_error_count += 1
+
+            # Log every 1000th error to avoid spam while still alerting users
+            if self._flush_error_count % 1000 == 0:
+                # Use print to avoid recursive logging issues
+                print(
+                    f"WARNING: {self._flush_error_count} log flush errors encountered "
+                    f"(Windows file handle issue). Logging continues but some debug "
+                    f"messages may be delayed or lost. Error: {e}",
+                    file=sys.stderr
+                )
+
+
 def setup_logging(
     info_log_filename: Optional[Path] = None,
     debug_log_filename: Optional[Path] = None,
@@ -50,14 +94,16 @@
     default_info_f = f"network_wrangler_{datetime.now().strftime('%Y_%m_%d__%H_%M_%S')}.info.log"
     info_log_filename = info_log_filename or Path.cwd() / default_info_f
 
-    info_file_handler = logging.FileHandler(Path(info_log_filename), mode=file_mode)
+    # Use SafeFileHandler instead of FileHandler to handle Windows flush errors
+    info_file_handler = SafeFileHandler(Path(info_log_filename), mode=file_mode)
     info_file_handler.setLevel(logging.INFO)
     info_file_handler.setFormatter(FORMAT)
     WranglerLogger.addHandler(info_file_handler)
 
     # create debug file only when debug_log_filename is provided
     if debug_log_filename:
-        debug_log_handler = logging.FileHandler(Path(debug_log_filename), mode=file_mode)
+        # Use SafeFileHandler instead of FileHandler to handle Windows flush errors
+        debug_log_handler = SafeFileHandler(Path(debug_log_filename), mode=file_mode)
         debug_log_handler.setLevel(logging.DEBUG)
         debug_log_handler.setFormatter(FORMAT)
         WranglerLogger.addHandler(debug_log_handler)