heurist-api 0.1.4__tar.gz → 0.2.1__tar.gz

{heurist_api-0.1.4 → heurist_api-0.2.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: heurist-api
-Version: 0.1.4
+Version: 0.2.1
 Dynamic: Description
 Dynamic: Description-Content-Type
 Summary: API wrapper and CLI for Heurist database.

{heurist_api-0.1.4 → heurist_api-0.2.1}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "heurist-api"
-version = "0.1.4"
+version = "0.2.1"
 description = "API wrapper and CLI for Heurist database."
 keywords = [ "duckdb", "etl" ]
 dynamic = [ "readme" ]
@@ -56,6 +56,7 @@ dev = [
 
 [project.scripts]
 heurist = "heurist.cli.__main__:cli"
+heurist-log = "heurist.cli.parse_log:cli"
 
 [tool.isort]
 profile = "black"

{heurist_api-0.1.4 → heurist_api-0.2.1}/src/heurist/cli/load.py

@@ -7,8 +7,14 @@ from pathlib import Path
 import duckdb
 from heurist.api.connection import HeuristAPIConnection
 from heurist.api.credentials import CredentialHandler
+from heurist.log import log_summary
+from heurist.log.constants import VALIDATION_LOG
 from heurist.utils.constants import DEFAULT_RECORD_GROUPS
 from heurist.workflows import extract_transform_load
+from rich.columns import Columns
+from rich.console import Console, Group
+from rich.padding import Padding
+from rich.panel import Panel
 
 
 def load_command(
@@ -37,10 +43,11 @@ def load_command(
         )
 
     # Show the results of the created DuckDB database
-    with duckdb.connect(duckdb_database_connection_path) as new_conn:
-        tables = new_conn.sql("show tables;")
-        print("\nCreated the following tables")
-        print(tables)
+    with duckdb.connect(duckdb_database_connection_path, read_only=True) as new_conn:
+        tables = [t[0] for t in new_conn.sql("show tables;").fetchall()]
+        with open(VALIDATION_LOG) as f:
+            log = f.readlines()
+        show_summary_in_console(tables=tables, log_lines=log)
 
         # If writing to CSV files, write only tables of record types
         if outdir:
@@ -53,3 +60,15 @@ def load_command(
                     continue
                 fp = outdir.joinpath(f"{table_name}.csv")
                 new_conn.table(table_name).sort("H-ID").write_csv(str(fp))
+
+
+def show_summary_in_console(tables: list[str], log_lines: list[str]):
+    console = Console()
+    t0 = Panel(
+        Columns(tables, equal=True, expand=True),
+        title="SQL Tables",
+        subtitle="Saved in DuckDB database file.",
+    )
+    t1, t2 = log_summary(lines=log_lines)
+    panel_group = Group(Padding(t0, 1), t1, Padding(t2, 1))
+    console.print(panel_group)

heurist_api-0.2.1/src/heurist/cli/parse_log.py

@@ -0,0 +1,27 @@
+import csv
+from pathlib import Path
+
+import click
+from heurist.log import LogDetail, yield_log_blocks
+from heurist.log.constants import VALIDATION_LOG
+
+log_detail_fieldnames = list(LogDetail.__annotations__.keys())
+
+
+@click.command()
+@click.option("-l", "--log-file", required=None, default=VALIDATION_LOG)
+@click.option("-o", "--outfile", required=None, default="invalid_records.csv")
+def cli(log_file, outfile):
+    logfile = Path(log_file)
+    if not logfile.is_file():
+        raise FileNotFoundError(log_file)
+    with open(logfile) as f, open(outfile, "w") as of:
+        writer = csv.DictWriter(of, fieldnames=log_detail_fieldnames)
+        writer.writeheader()
+        lines = f.readlines()
+        for block in yield_log_blocks(lines):
+            writer.writerow(block.__dict__)
+
+
+if __name__ == "__main__":
+    cli()

heurist_api-0.2.1/src/heurist/log/__init__.py

@@ -0,0 +1,3 @@
+from .iterator import yield_log_blocks as yield_log_blocks
+from .model import LogDetail as LogDetail
+from .summary import log_summary as log_summary

heurist_api-0.2.1/src/heurist/log/constants.py

@@ -0,0 +1,4 @@
+from pathlib import Path
+
+VALIDATION_LOG = Path.cwd().joinpath("validation.log")
+VALIDATION_LOG.touch(exist_ok=True)

heurist_api-0.2.1/src/heurist/log/iterator.py

@@ -0,0 +1,16 @@
+from typing import Generator
+
+from .model import LogDetail
+
+
+def yield_log_blocks(lines: list[str]) -> Generator[LogDetail, None, None]:
+    line_iterator = iter(lines)
+    l1 = next(line_iterator, None)
+    while l1 is not None:
+        if l1 and not l1.startswith("\t"):
+            l2 = next(line_iterator)
+            l3 = next(line_iterator)
+            l4 = next(line_iterator)
+            l5 = next(line_iterator)
+            yield LogDetail.load_lines(l1, l2, l3, l4, l5)
+        l1 = next(line_iterator, None)

heurist_api-0.2.1/src/heurist/log/model.py

@@ -0,0 +1,42 @@
+import re
+from dataclasses import dataclass
+
+
+@dataclass
+class LogDetail:
+    time: str
+    level: str
+    recType: int
+    recID: int
+    rule: str
+    problem: str
+
+    @classmethod
+    def load_lines(cls, *block_lines) -> "LogDetail":
+        l1, l2, l3, l4, l5 = block_lines
+        for indented_line in [l2, l3, l4, l5]:
+            assert indented_line.startswith("\t")
+        return LogDetail(
+            time=cls.parse_time(l1),
+            level=cls.parse_level(l1),
+            recType=cls.parse_number(l2),
+            recID=cls.parse_number(l3),
+            rule=l4.removeprefix("\t").strip(),
+            problem=l5.removeprefix("\t").strip(),
+        )
+
+    @staticmethod
+    def parse_number(line) -> int:
+        parts = line.split()
+        suffix: str = parts[-1]
+        number = suffix.removesuffix("]")
+        return int(number)
+
+    @staticmethod
+    def parse_time(l1: str) -> str:
+        parts = l1.split(" - ")
+        return parts[0].strip()
+
+    @staticmethod
+    def parse_level(l1: str) -> str:
+        return re.search(r"[A-Z]+", l1).group(0).strip()

heurist_api-0.2.1/src/heurist/log/summary.py

@@ -0,0 +1,35 @@
+from collections import Counter
+
+from heurist.log import yield_log_blocks
+from rich.table import Table
+
+
+def log_summary(lines: list[str]) -> tuple[Table, Table]:
+    rectypes = []
+    recs = []
+    for block in yield_log_blocks(lines):
+        rectypes.append(block.recType)
+        recs.append(block.recID)
+
+    rectype_counter = Counter(rectypes)
+    rec_counter = Counter(recs)
+
+    rec_table = Table(
+        title="Most problematic records",
+        caption="Note: Invalid records are not saved in the DuckDB database.",
+    )
+    rec_table.add_column("Record ID", style="red")
+    rec_table.add_column("Number of problems")
+    for rec, count in rec_counter.most_common(10):
+        rec_table.add_row(str(rec), str(count))
+
+    type_table = Table(
+        title="Types of invalid records",
+        caption="Note: Invalid records are not saved in the DuckDB database.",
+    )
+    type_table.add_column("Record Type", style="red")
+    type_table.add_column("Number of records")
+    for rec, count in rectype_counter.items():
+        type_table.add_row(str(rec), str(count))
+
+    return type_table, rec_table

{heurist_api-0.1.4 → heurist_api-0.2.1}/src/heurist/validators/record_validator.py

@@ -1,15 +1,13 @@
 import logging
 import os
-from pathlib import Path
 
+from heurist.log.constants import VALIDATION_LOG
 from heurist.models.dynamic.annotation import PydanticField
 from heurist.models.dynamic.type import FieldType
 from heurist.validators.detail_validator import DetailValidator
 from heurist.validators.exceptions import RepeatedValueInSingularDetailType
 from pydantic import BaseModel
 
-VALIDATION_LOG = Path.cwd().joinpath("validation.log")
-
 handlers = [logging.FileHandler(filename=VALIDATION_LOG, mode="w", delay=True)]
 if os.getenv("HEURIST_STREAM_LOG") == "True":
     handlers.append(logging.StreamHandler())

heurist_api-0.2.1/tests/unit/log_test.py

@@ -0,0 +1,44 @@
+import unittest
+from pathlib import Path
+
+from heurist.log import yield_log_blocks, LogDetail
+
+
+LOG_FILE = Path(__file__).parent.joinpath("mock_log.txt")
+
+LINES = [
+    "2025-05-26 18:50 - WARNING - ",
+    "	[rec_Type 104]",
+    "	[rec_ID 834]",
+    "	The detail 'note' is limited to a maximum of 1 values.",
+    "	Count of values = 3.",
+    "2025-05-26 18:50 - WARNING - ",
+    "	[rec_Type 104]",
+    "	[rec_ID 834]",
+    "	The detail 'contam' is limited to a maximum of 1 values.",
+    "	Count of values = 2.",
+]
+
+
+class TestLog(unittest.TestCase):
+    def assess_log_block(self, log: LogDetail):
+        self.assertEqual(log.level, "WARNING")
+        self.assertIsNotNone(log.rule)
+        self.assertIsNotNone(log.problem)
+        self.assertGreater(log.recID, 100)
+        self.assertGreater(log.recType, 99)
+
+    def test_parsed_lines(self):
+        for log in yield_log_blocks(LINES):
+            self.assess_log_block(log)
+
+    def test_log_file(self):
+        print(LOG_FILE)
+        with open(LOG_FILE) as f:
+            lines = f.readlines()
+            for log in yield_log_blocks(lines):
+                self.assess_log_block(log)
+
+
+if __name__ == "__main__":
+    unittest.main()

{heurist_api-0.1.4 → heurist_api-0.2.1}/uv.lock

@@ -421,7 +421,7 @@ wheels = [
 
 [[package]]
 name = "heurist-api"
-version = "0.1.3"
+version = "0.2.1"
 source = { editable = "." }
 dependencies = [
     { name = "click" },
@@ -438,7 +438,7 @@ dependencies = [
     { name = "tenacity" },
 ]
 
-[package.dev-dependencies]
+[package.optional-dependencies]
 dev = [
     { name = "coverage" },
     { name = "genbadge", extra = ["coverage"] },
@@ -458,35 +458,32 @@ dev = [
 [package.metadata]
 requires-dist = [
     { name = "click", specifier = ">=8.2.0" },
+    { name = "coverage", marker = "extra == 'dev'", specifier = ">=7.8.0" },
     { name = "duckdb", specifier = ">=1.2.2" },
+    { name = "genbadge", extras = ["coverage"], marker = "extra == 'dev'", specifier = ">=1.1.2" },
+    { name = "isort", marker = "extra == 'dev'", specifier = ">=6.0.1" },
     { name = "lxml", specifier = ">=5.4.0" },
+    { name = "mkdocs", marker = "extra == 'dev'", specifier = ">=1.6.1" },
+    { name = "mkdocs-gen-files", marker = "extra == 'dev'", specifier = ">=0.5.0" },
+    { name = "mkdocs-literate-nav", marker = "extra == 'dev'", specifier = ">=0.6.2" },
+    { name = "mkdocs-material", extras = ["imaging"], marker = "extra == 'dev'", specifier = ">=9.6.14" },
+    { name = "mkdocstrings-python", marker = "extra == 'dev'", specifier = ">=1.16.10" },
     { name = "pandas", specifier = ">=2.2.3" },
     { name = "polars", specifier = ">=1.29.0" },
+    { name = "pre-commit", marker = "extra == 'dev'", specifier = ">=4.2.0" },
     { name = "pyarrow", specifier = ">=20.0.0" },
     { name = "pydantic", specifier = ">=2.11.4" },
     { name = "pydantic-xml", specifier = ">=2.16.0" },
+    { name = "pymdown-extensions", marker = "extra == 'dev'", specifier = ">=10.15" },
+    { name = "pytest", marker = "extra == 'dev'", specifier = ">=8.3.5" },
     { name = "python-dotenv", specifier = ">=1.1.0" },
     { name = "requests", specifier = ">=2.32.3" },
     { name = "rich", specifier = ">=14.0.0" },
+    { name = "ruff", marker = "extra == 'dev'", specifier = ">=0.11.10" },
     { name = "tenacity", specifier = ">=9.1.2" },
+    { name = "uv", marker = "extra == 'dev'", specifier = ">=0.7.5" },
 ]
-
-[package.metadata.requires-dev]
-dev = [
-    { name = "coverage", specifier = ">=7.8.0" },
-    { name = "genbadge", extras = ["coverage"], specifier = ">=1.1.2" },
-    { name = "isort", specifier = ">=6.0.1" },
-    { name = "mkdocs", specifier = ">=1.6.1" },
-    { name = "mkdocs-gen-files", specifier = ">=0.5.0" },
-    { name = "mkdocs-literate-nav", specifier = ">=0.6.2" },
-    { name = "mkdocs-material", extras = ["imaging"], specifier = ">=9.6.14" },
-    { name = "mkdocstrings-python", specifier = ">=1.16.10" },
-    { name = "pre-commit", specifier = ">=4.2.0" },
-    { name = "pymdown-extensions", specifier = ">=10.15" },
-    { name = "pytest", specifier = ">=8.3.5" },
-    { name = "ruff", specifier = ">=0.11.10" },
-    { name = "uv", specifier = ">=0.7.5" },
-]
+provides-extras = ["dev"]
 
 [[package]]
 name = "identify"