commit 56e34902bb3367059e234d69cebf9eba9d23307c
Author: Arti Zirk <arti.zirk@gmail.com>
Date:   Sat Nov 6 20:02:09 2021 +0200

    Imports

diff --git a/.gitignore b/.gitignore
new file mode 100644
index 0000000..a886f03
--- /dev/null
+++ b/.gitignore
@@ -0,0 +1,140 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+.idea
+smartmontools
diff --git a/README.md b/README.md
new file mode 100644
index 0000000..61a3e72
--- /dev/null
+++ b/README.md
@@ -0,0 +1,2 @@
+# Load smartmontools attrlog files to PostgreSQL
+For luls and pretty Grafana graphs
diff --git a/attrlogimport.py b/attrlogimport.py
new file mode 100755
index 0000000..5a0744a
--- /dev/null
+++ b/attrlogimport.py
@@ -0,0 +1,78 @@
+#!/usr/bin/env python3
+import os
+import re
+import sys
+
+import psycopg
+
+drive_name_re = re.compile(r'attrlog\.(.*).ata.csv')
+
+conn = psycopg.connect("dbname=smartmontools")
+
+
+def create_tables():
+    with conn.cursor() as cur:
+        cur.execute("START TRANSACTION")
+        cur.execute("""
+            CREATE TABLE device (
+                id serial primary key,
+                name text
+            )""")
+        cur.execute("""
+            CREATE TABLE attrlog (
+                time timestamptz not null,
+                device_id integer references device(id) not null,
+                id smallint not null,
+                norm smallint,
+                raw bigint,
+                unique (time, device_id, id)
+            )
+        """)
+        cur.execute("COMMIT")
+
+
+def create_or_find_device_id(name):
+    with conn.cursor() as cur:
+        cur.execute("SELECT id FROM device WHERE name = %s", (name,))
+        row = cur.fetchone()
+        if row is None:
+            cur.execute("INSERT INTO device (name) VALUES (%s) RETURNING id", (name,))
+            row = cur.fetchone()
+        return row[0]
+
+
+def parse_attrlog_file(filename, device_id=None):
+    fd = open(filename)
+    file_size = fd.seek(0, os.SEEK_END)
+    fd.seek(0)
+    while fd.tell() != file_size:
+        line = fd.readline()
+        line_parts = [p for p in line.strip().split(";") if p.strip()]
+        dt = line_parts.pop(0)+"+0200"
+        while line_parts:
+            id = int(line_parts.pop(0))
+            norm = int(line_parts.pop(0))
+            raw = int(line_parts.pop(0))
+            yield dt, id, norm, raw, device_id
+            if fd.tell() % 100 == 0:
+                print(f"{int((fd.tell() / file_size)*100):>5}%", end='\r')
+    print()
+
+
+def import_attrlog_file(filename):
+    drive_name = drive_name_re.search(filename).group(1)
+    print(drive_name)
+    device_id = create_or_find_device_id(drive_name)
+    with conn.cursor() as cur:
+        cur.execute("START TRANSACTION")
+        with cur.copy("copy attrlog (time, id, norm, raw, device_id) FROM STDIN") as copy:
+            for row in parse_attrlog_file(filename, device_id):
+                copy.write_row(row)
+        cur.execute("COMMIT")
+
+
+if __name__ == '__main__':
+    if len(sys.argv) < 2:
+        create_tables()
+    else:
+        import_attrlog_file(sys.argv[1])