Add geothermal electricity extraction support

compass/_cli/process.py

@@ -2,9 +2,13 @@
 
 import asyncio
 import logging
+import shutil
+import sys
 import warnings
 import multiprocessing
 
+from pathlib import Path
+
 import click
 from rich.live import Live
 from rich.theme import Theme
@@ -14,8 +18,11 @@
 from compass.pb import COMPASS_PB
 from compass.plugin import create_schema_based_one_shot_extraction_plugin
 from compass.scripts.process import process_jurisdictions_with_openai
-from compass.utilities.logs import AddLocationFilter
 from compass.utilities.io import load_config
+from compass.utilities.logs import AddLocationFilter
+
+
+OUT_DIR_POLICY_CHOICES = ["fail", "increment", "overwrite", "prompt"]
 
 
 @click.command
@@ -49,10 +56,24 @@
     default=None,
     help="One-shot plugin configuration to add to COMPASS before processing",
 )
-def process(config, verbose, no_progress, plugin):
+@click.option(
+    "--out_dir_exists",
+    required=False,
+    default=None,
+    type=click.Choice(OUT_DIR_POLICY_CHOICES, case_sensitive=False),
+    help="How to handle an existing output directory."
+    " Choices: fail, increment, overwrite, prompt."
+    " If omitted, prompts interactively when running in a terminal,"
+    " or fails when running non-interactively (e.g. CI).",
+)
+def process(config, verbose, no_progress, plugin, out_dir_exists):
     """Download and extract ordinances for a list of jurisdictions"""
     config = load_config(config)
 
+    config["out_dir"] = _resolve_out_dir_conflict(
+        config["out_dir"], out_dir_exists
+    )
+
     if plugin is not None:
         create_schema_based_one_shot_extraction_plugin(
             config=plugin, tech=config["tech"]
@@ -128,3 +149,101 @@ def _setup_cli_logging(console, verbosity_level, log_level="INFO"):
         handler.addFilter(AddLocationFilter())
         logger.addHandler(handler)
         logger.setLevel(log_level)
+
+
+def _resolve_out_dir_conflict(out_dir, policy):
+    """Handle existing output directory using the selected policy"""
+    out_dir = Path(out_dir)
+    policy = _resolve_out_dir_policy(policy)
+
+    if not out_dir.exists() or policy == "fail":
+        return out_dir
+
+    if policy == "increment":
+        new_out_dir = _next_versioned_directory(out_dir)
+        click.echo(
+            "Output directory exists. "
+            f"Using incremented directory: {new_out_dir!s}"
+        )
+        return new_out_dir
+
+    if policy == "overwrite":
+        click.echo(f"Overwriting existing output directory: {out_dir!s}")
+        shutil.rmtree(out_dir)
+        return out_dir
+
+    if policy == "prompt":
+        return _resolve_prompt_out_dir_conflict(out_dir)
+
+    msg = (
+        f"Unknown out_dir_exists policy '{policy}'. "
+        f"Supported values: {OUT_DIR_POLICY_CHOICES}."
+    )
+    raise click.ClickException(msg)
+
+
+def _next_versioned_directory(out_dir):
+    """
+    Create the next available output directory suffix with
+    versioning
+    """
+    idx = 2
+    max_idx = 1_000_000
+    while idx <= max_idx:
+        candidate = out_dir.parent / f"{out_dir.name}_v{idx}"
+        if not candidate.exists():
+            return candidate
+        idx += 1
+
+    msg = (
+        f"Unable to find an available versioned directory for '{out_dir!s}' "
+        f"up to suffix _v{max_idx}."
+    )
+    raise click.ClickException(msg)
+
+
+def _resolve_out_dir_policy(policy):
+    """Resolve output directory policy from explicit input
+
+    Falls back to terminal mode defaults when no policy is set.
+    """
+    if policy is not None:
+        return policy.lower()
+    if sys.stdin.isatty():
+        return "prompt"
+    return "fail"
+
+
+def _resolve_prompt_out_dir_conflict(out_dir):
+    """Handle interactive prompt flow for existing output directory"""
+    if not sys.stdin.isatty():
+        msg = (
+            "Cannot use out_dir_exists='prompt' in non-interactive mode. "
+            "Use one of: fail, increment, overwrite."
+        )
+        raise click.ClickException(msg)
+
+    create_incremented = click.confirm(
+        f"Output directory '{out_dir!s}' already exists. "
+        "Create a new incremented directory automatically?",
+        default=True,
+    )
+    if create_incremented:
+        new_out_dir = _next_versioned_directory(out_dir)
+        click.echo(f"Using incremented directory: {new_out_dir!s}")
+        return new_out_dir
+
+    overwrite = click.confirm(
+        f"Overwrite '{out_dir!s}' by deleting it and continuing?",
+        default=False,
+    )
+    if overwrite:
+        click.echo(f"Overwriting existing output directory: {out_dir!s}")
+        shutil.rmtree(out_dir)
+        return out_dir
+
+    msg = (
+        "Run cancelled. Please update out_dir in config, or rerun with "
+        "--out_dir_exists increment/overwrite."
+    )
+    raise click.ClickException(msg)

compass/extraction/geothermal_electricity/geothermal_plugin_config.yaml

@@ -0,0 +1,144 @@
+schema: ./geothermal_schema.json
+
+data_type_short_desc: utility-scale geothermal electricity ordinance
+
+cache_llm_generated_content: true
+
+query_templates:
+    - "filetype:pdf {jurisdiction} geothermal power plant ordinance"
+    - "geothermal electricity generation ordinance {jurisdiction}"
+    - "{jurisdiction} geothermal energy facility zoning ordinance"
+    - "{jurisdiction} geothermal power plant land use code"
+    - "{jurisdiction} geothermal code of ordinances"
+
+website_keywords:
+    pdf: 92160
+    geothermal: 46080
+    ordinance: 23040
+    zoning: 11520
+    regulation: 5760
+    code: 2880
+    power: 1440
+    electricity: 1440
+    planning: 720
+    permit: 720
+    land use: 720
+    municipal: 720
+    county: 360
+    ordinance code: 360
+    code of ordinances: 360
+    land use code: 360
+    use table: 360
+    chapter: 180
+    article: 180
+    title: 180
+    statute: 180
+    administrative code: 180
+    conditional use permit: 180
+    special use permit: 180
+    drilling permit: 180
+    resource development: 180
+    government: 180
+
+heuristic_keywords:
+  good_tech_keywords:
+    - "wellfield"
+    - "brine"
+  good_tech_acronyms:
+    - "egs"
+    - "kgra"
+  good_tech_phrases:
+    - "well field"
+    - "production well"
+    - "geothermal exploration"
+    - "geothermal generating"
+    - "geothermal generation"
+    - "geothermal power"
+    - "geothermal power plant"
+    - "geothermal production"
+    - "geothermal project"
+    - "geothermal overlay zone"
+    - "geothermal facility"
+    - "geothermal electric"
+    - "geothermal electricity generation"
+    - "geothermal energy facility"
+    - "geothermal resource"
+    - "geothermal resource development"
+    - "known geothermal resource area"
+    - "geothermal production project"
+    - "geothermal drilling"
+    - "geothermal lease"
+    - "geothermal development"
+    - "geothermal well"
+    - "geothermal reservoir"
+    - "binary cycle"
+    - "flash steam"
+    - "dry steam"
+    - "steam turbine"
+    - "enhanced geothermal"
+    - "reservoir temperature"
+    - "reinjection well"
+    - "production zone"
+    - "exploratory well"
+    - "injection well"
+    - "drilling permit"
+    - "plan of utilization"
+  not_tech_words:
+    - "geothermal heat pump"
+    - "ground source heat pump"
+    - "ground-source heat pump"
+    - "ghp"
+    - "ground heat pump"
+    - "gshp"
+    - "ground-coupled heat pump"
+    - "ground coupled heat pump"
+    - "earth-coupled heat pump"
+    - "earth-source heat pump"
+    - "geoexchange"
+    - "geo-exchange"
+    - "closed loop"
+    - "closed-loop"
+    - "open loop"
+    - "vertical loop"
+    - "horizontal loop"
+    - "heating and cooling"
+    - "hvac"
+    - "space heating"
+    - "water heating"
+    - "direct use"
+    - "direct-use"
+    - "district heating"
+    - "greenhouse heating"
+    - "residential geothermal"
+    - "accessory use"
+    - "energy star"
+    - "solar panel"
+    - "solar array"
+    - "solar farm"
+    - "solar energy system"
+    - "solar energy facility"
+    - "photovoltaic"
+    - "net metering"
+    - "solar collector"
+    - "solar ordinance"
+    - "wind energy"
+    - "wind farm"
+    - "wind turbine"
+    - "wind energy system"
+    - "wind energy facility"
+    - "wind energy conversion"
+    - "wind ordinance"
+    - "anemometer tower"
+    - "meteorological tower"
+    - "rotor diameter"
+    - "tip height"
+    - "nacelle"
+    - "battery storage"
+    - "energy storage system"
+    - "hydroelectric"
+    - "biomass"
+    - "cannabis"
+    - "cannabis cultivation"
+    - "commercial cannabis"
+
+collection_prompts: True