requake 0.8__tar.gz → 0.8.1__tar.gz

{requake-0.8 → requake-0.8.1}/CHANGELOG.md

@@ -2,6 +2,30 @@
 
 Copyright (c) 2021-2026 Claudio Satriano <satriano@ipgp.fr>
 
+## [0.8.1] - 2026-05-31
+
+- Slimmed-down DB size by optimizing `event_pairs` storage. This allows storing
+  also invalid pairs, so that resuming catalog scan is faster.
+- Dramatic speedup of event pairs building by using a KD-tree
+  spatial index and approximate geodetic distance calculations.
+- Dramatic speedup of waveform fetching by improving the caching mechanism.
+  A new config option `catalog_waveform_cache_size` allows to set the maximum
+  number of waveforms to cache.
+- Dramatically faster reading of event pairs with cross-correlation
+  filters in large catalogs, thanks to the new SQLite-backed storage.
+- Add an optional disk cache, through the `catalog_waveform_disk_cache_enabled`
+  config option.
+- `scan_catalog`: when running as a batch job, log a progress
+  report every minute, instead of showing the progress bar.
+- `scan_catalog`: if event pairs already exist in the database,
+  ask whether to overwrite or continue from an interrupted run.
+  Add `--force` to restart from scratch and `--force-continue`
+  (short `-c`) to resume without prompting.
+- `print_families`: add horizontal and vertical distance min/max values
+  to both summary and detailed (`-d`) outputs.
+- `print_families`: add `-f stats` output format for summary family
+  statistics.
+
 ## [0.8] - 2026-05-22
 
 This release introduces a major storage change.
@@ -13,6 +37,9 @@ data access performance, especially for large catalogs.
 This change is not backward compatible at the data format level. The
 high-level behavior of the command-line interface remains unchanged.
 
+Note: further improvements based on this new storage system will be introduced
+throughout the 0.8.x release series.
+
 ## [0.7.3] - 2026-04-14
 
 This release is intended to validate the new release workflow.
@@ -151,6 +178,7 @@ Mostly a bugfix release with a slightly improved trace plotting.
 
 - Initial release, not yet feature complete
 
+[0.8.1]: https://github.com/SeismicSource/requake/compare/v0.8...v0.8.1
 [0.8]: https://github.com/SeismicSource/requake/compare/v0.7.3...v0.8
 [0.7.3]: https://github.com/SeismicSource/requake/compare/v0.7.2...v0.7.3
 [0.7.2]: https://github.com/SeismicSource/requake/compare/v0.7.1...v0.7.2

{requake-0.8 → requake-0.8.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: requake
-Version: 0.8
+Version: 0.8.1
 Summary: Repeating earthquakes search and analysis
 Author-email: Claudio Satriano <satriano@ipgp.fr>
 License-Expression: GPL-3.0-or-later
@@ -37,7 +37,7 @@ Dynamic: description
 Dynamic: description-content-type
 Dynamic: license-file
 
-<img src="https://cdn.jsdelivr.net/gh/SeismicSource/requake@e3ac4cce14f782d62a5f22f432a5391a2ccacfe7/imgs/Requake_logo.svg" width="400">
+<img src="https://cdn.jsdelivr.net/gh/SeismicSource/requake@166143d5bcff5dced4ef1b9a3cc7c746b0cc1b63/imgs/Requake_logo.svg" width="400">
 
 # Requake
 

{requake-0.8 → requake-0.8.1}/requake/_version.py

@@ -8,11 +8,11 @@ import json
 
 version_json = '''
 {
- "date": "2026-05-22T08:53:09+0200",
+ "date": "2026-05-31T15:55:08+0200",
  "dirty": false,
  "error": null,
- "full-revisionid": "e3ac4cce14f782d62a5f22f432a5391a2ccacfe7",
- "version": "0.8"
+ "full-revisionid": "166143d5bcff5dced4ef1b9a3cc7c746b0cc1b63",
+ "version": "0.8.1"
 }
 '''  # END VERSION_JSON
 

{requake-0.8 → requake-0.8.1}/requake/catalog/catalog.py

@@ -11,7 +11,6 @@ Classes and functions for downloading, reading and writing catalogs.
 """
 import numpy as np
 from obspy import UTCDateTime
-from ..config import config
 from ..formulas import float_or_none
 from ..waveforms import get_traceid_coords
 
@@ -230,7 +229,7 @@ def read_stored_catalog():
     """
     from ..database.catalog import read_catalog as read_catalog_from_db
 
-    cat = read_catalog_from_db(config)
+    cat = read_catalog_from_db()
     cat.sort()
     if not cat:
         raise ValueError('Empty catalog')
@@ -246,7 +245,7 @@ def fix_non_locatable_events(catalog):
     """
     if not any(ev.lat is None or ev.lon is None for ev in catalog):
         return
-    traceid_coords = get_traceid_coords(config)
+    traceid_coords = get_traceid_coords()
     mean_lat = np.mean([
         coords['latitude'] for coords in traceid_coords.values()])
     mean_lon = np.mean([

{requake-0.8 → requake-0.8.1}/requake/catalog/read_catalog.py

@@ -117,8 +117,8 @@ def read_catalog():
             catalog = read_stored_catalog()
             nevs_read = len(catalog)
             logger.info(
-                f'{nevs_read} events read from db file '
-                f'{get_db_path(config)}'
+                f'{nevs_read:n} events read from db file '
+                f'{get_db_path()}'
             )
     logger.info('Reading catalog...')
     input_cat_file = config.args.catalog_file
@@ -150,9 +150,9 @@ def read_catalog():
     # Sort catalog in increasing time order
     catalog.sort()
     # Write catalog to the output database
-    write_stored_catalog(catalog, config)
+    write_stored_catalog(catalog)
     nevs_written = len(catalog) - nevs_read
     logger.info(
-        f'{nevs_written} events written to db file '
-        f'{get_db_path(config)}'
+        f'{nevs_written:n} events written to db file '
+        f'{get_db_path()}'
     )

{requake-0.8 → requake-0.8.1}/requake/config/configspec.conf

@@ -68,6 +68,14 @@ catalog_search_range = float(default=30)
 ## If more than one trace_id is specified (separated by commas), the closest
 ## station will be used for a given event pair.
 catalog_trace_id = force_list(default=NET.STA.LOC.CHAN)
+## Maximum number of event waveforms kept in memory cache during
+## catalog-based scan. Higher values increase memory usage and can reduce
+## repeated waveform downloads.
+catalog_waveform_cache_size = integer(min=2, default=5000)
+## Keep a persistent copy of fetched event waveforms on disk to speed up
+## reruns. This on-disk cache lives in OUTDIR/waveform_cache and is not
+## limited by catalog_waveform_cache_size.
+catalog_waveform_disk_cache_enabled = boolean(default=true)
 
 #### Template-based scan
 ### The following parameters are for template-based scan:

{requake-0.8 → requake-0.8.1}/requake/config/parse_arguments.py

@@ -160,11 +160,23 @@ def parse_arguments(progname='requake'):
     )
     # ---
     # --- scan_catalog
-    subparser.add_parser(
+    scan_catalog = subparser.add_parser(
         'scan_catalog',
-        parents=[force],
         help='scan an existing catalog for earthquake pairs'
     )
+    scan_catalog_mode = scan_catalog.add_mutually_exclusive_group()
+    scan_catalog_mode.add_argument(
+        '-f',
+        '--force',
+        action='store_true',
+        help='delete existing event pairs and restart the scan'
+    )
+    scan_catalog_mode.add_argument(
+        '-c',
+        '--force-continue',
+        action='store_true',
+        help='continue an interrupted scan and keep existing event pairs'
+    )
     # ---
     # --- print_pairs
     print_pairs = subparser.add_parser(
@@ -324,10 +336,15 @@ def parse_arguments(progname='requake'):
     print_families = subparser.add_parser(
         'print_families',
         parents=[
-            longerthan, shorterthan, minevents, family_numbers, print_format
+            longerthan, shorterthan, minevents, family_numbers
         ],
         help='print families to screen'
     )
+    print_families.add_argument(
+        '-f', '--format', type=str, default='simple',
+        choices=['simple', 'markdown', 'csv', 'stats'],
+        help='format for the output (default: %(default)s)'
+    )
     print_families.add_argument(
         '-d', '--detailed', action='store_true',
         help='print detailed information for each family, including a list '

{requake-0.8 → requake-0.8.1}/requake/config/rq_setup.py

@@ -273,7 +273,7 @@ def configure(args):
     should_write_catalog = (
         args.action == 'read_catalog'
         and not args.append
-        and not write_ok(get_db_path(config), args.force)
+        and not write_ok(get_db_path(), args.force)
     )
     if should_write_catalog:
         print('Exiting now.')

{requake-0.8 → requake-0.8.1}/requake/database/catalog.py

@@ -86,9 +86,9 @@ def _event_from_row(row):
     )
 
 
-def write_catalog(catalog, config, db_path=None):
+def write_catalog(catalog, db_path=None):
     """Write the stored catalog into SQLite."""
-    conn = get_db_connection(config, initdb=True, db_path=db_path)
+    conn = get_db_connection(initdb=True, db_path=db_path)
     try:
         cursor = conn.cursor()
         _ensure_catalog_table(cursor)
@@ -112,11 +112,11 @@ def write_catalog(catalog, config, db_path=None):
         conn.close()
 
 
-def read_catalog(config, db_path=None):
+def read_catalog(db_path=None):
     """Read the stored catalog from SQLite."""
     from ..catalog.catalog import RequakeCatalog
 
-    conn = get_db_connection(config, initdb=False, db_path=db_path)
+    conn = get_db_connection(initdb=False, db_path=db_path)
     try:
         rows = conn.execute(
             f'SELECT * FROM {CATALOG_TABLE} ORDER BY orig_time'
@@ -125,7 +125,7 @@ def read_catalog(config, db_path=None):
         if MISSING_CATALOG_TABLE in str(err):
             raise FileNotFoundError(
                 'Catalog not found in db file '
-                f'{get_db_path(config, db_path=db_path)}'
+                f'{get_db_path(db_path=db_path)}'
             ) from err
         raise
     finally:

{requake-0.8 → requake-0.8.1}/requake/database/db.py

@@ -14,6 +14,7 @@ import contextlib
 import random
 import sqlite3
 import time
+from ..config.config import config
 
 DB_VERSION = 1
 DB_FILENAME = 'requake.sqlite'
@@ -29,7 +30,11 @@ class DatabaseBusyError(RuntimeError):
     """Raised when retries for transient SQLite lock errors are exhausted."""
 
 
-def get_db_path(config, db_path=None):
+class DatabaseCorruptError(RuntimeError):
+    """Raised when the SQLite database file is corrupt or malformed."""
+
+
+def get_db_path(db_path=None):
     """Return the SQLite path."""
     if db_path is not None:
         return db_path
@@ -61,9 +66,9 @@ def get_db_path(config, db_path=None):
     return os.path.join(outdir, DB_FILENAME)
 
 
-def check_db_exists(config, initdb=False, db_path=None):
+def check_db_exists(initdb=False, db_path=None):
     """Validate the configured database path for read or init mode."""
-    db_path = get_db_path(config, db_path=db_path)
+    db_path = get_db_path(db_path=db_path)
     if initdb:
         _ensure_parent_dir(db_path)
         return db_path
@@ -138,15 +143,15 @@ def execute_with_retry(operation, operation_name):
             attempt += 1
 
 
-def initialize_database_if_needed(config, db_path=None):
+def initialize_database_if_needed(db_path=None):
     """Initialize database schema version and pragmas if missing."""
-    conn = get_db_connection(config, initdb=True, db_path=db_path)
+    conn = get_db_connection(initdb=True, db_path=db_path)
     conn.close()
 
 
-def get_db_connection(config, initdb=False, db_path=None):
+def get_db_connection(initdb=False, db_path=None):
     """Open a SQLite connection for the configured database file."""
-    db_path = check_db_exists(config, initdb=initdb, db_path=db_path)
+    db_path = check_db_exists(initdb=initdb, db_path=db_path)
     conn = sqlite3.connect(db_path)
     _configure_connection(conn)
     conn.row_factory = sqlite3.Row

{requake-0.8 → requake-0.8.1}/requake/database/families.py

@@ -64,9 +64,9 @@ def _family_row(family, event):
     )
 
 
-def write_families(families, config):
+def write_families(families):
     """Write catalog-scan families into SQLite."""
-    conn = get_db_connection(config, initdb=True)
+    conn = get_db_connection(initdb=True)
     try:
         cursor = conn.cursor()
         _ensure_families_table(cursor)
@@ -95,12 +95,12 @@ def write_families(families, config):
         conn.close()
 
 
-def read_families(config):
+def read_families():
     """Read catalog-scan families from SQLite."""
     from ..catalog import RequakeEvent
     from ..families.families import Family
 
-    conn = get_db_connection(config, initdb=False)
+    conn = get_db_connection(initdb=False)
     try:
         cursor = conn.cursor()
         try:
@@ -113,7 +113,7 @@ def read_families(config):
         except sqlite3.OperationalError as err:
             if MISSING_FAMILIES_TABLE in str(err):
                 raise FileNotFoundError(
-                    f'Families not found in db file {get_db_path(config)}'
+                    f'Families not found in db file {get_db_path()}'
                 ) from err
             raise
     finally:
@@ -147,9 +147,9 @@ def read_families(config):
     return families
 
 
-def update_family_valid(config, family_number, is_valid):
+def update_family_valid(family_number, is_valid):
     """Update the validity flag for all events in one family."""
-    conn = get_db_connection(config, initdb=False)
+    conn = get_db_connection(initdb=False)
     try:
         cursor = conn.cursor()
         try:
@@ -166,7 +166,7 @@ def update_family_valid(config, family_number, is_valid):
         except sqlite3.OperationalError as err:
             if MISSING_FAMILIES_TABLE in str(err):
                 raise FileNotFoundError(
-                    f'Families not found in db file {get_db_path(config)}'
+                    f'Families not found in db file {get_db_path()}'
                 ) from err
             raise
         conn.commit()