python-materialsdb 0.0.1__tar.gz → 0.1.0__tar.gz

{python-materialsdb-0.0.1 → python_materialsdb-0.1.0}/PKG-INFO

@@ -1,6 +1,6 @@
-Metadata-Version: 2.1
+Metadata-Version: 2.4
 Name: python-materialsdb
-Version: 0.0.1
+Version: 0.1.0
 Summary: A library to work with materialsdb.org open standard for building materials.
 Home-page: https://github.com/CyrilWaechter/python-materialsdb
 Author: Cyril Waechter
@@ -9,15 +9,19 @@ License: GPLv3+
 Project-URL: Bug Tracker, https://github.com/CyrilWaechter/python-materialsdb/issues
 Project-URL: Community, https://community.osarch.org/
 Keywords: materials,BIM,ifcopenshell,IFC
-Platform: UNKNOWN
 Classifier: Programming Language :: Python :: 3
 Classifier: License :: OSI Approved :: GNU General Public License v3 or later (GPLv3+)
 Classifier: Operating System :: OS Independent
 Classifier: Topic :: Software Development :: Libraries :: Python Modules
 Classifier: Topic :: Scientific/Engineering
 Description-Content-Type: text/markdown
-Provides-Extra: ifc
 License-File: LICENSE.md
+Requires-Dist: lxml
+Provides-Extra: ifc
+Requires-Dist: ifcopenshell; extra == "ifc"
+Provides-Extra: dev
+Requires-Dist: pytest-benchmark; extra == "dev"
+Dynamic: license-file
 
 python-materialsdb is an unofficial python library for [materialsdb.org][1] an open format and database for building materials.
 
@@ -46,9 +50,21 @@ Note: in materialsdb standard languages are [ISO 639-1](https://en.wikipedia.org
 
 # Usage examples :
 Check out some [examples](examples):
-* [Convert lastest materials data to ifc](examples/generate_ifc_project_libraries.py)
+* [Convert latest materials data to ifc](examples/generate_ifc_project_libraries.py)
 * [Create your own materialsdb.org compliant XML](examples/create_layers.py)
 
+# Querying materials :
+The library keeps an sqlite index of the cached materials data for fast
+filtering and single-material access:
+
+```python
+from materialsdb import query
+
+query.refresh()                                   # incremental update from cached xml
+rows = query.search("isolant", sort="lambda")     # filtered, sorted summaries
+material = query.get_material(rows[0].id)         # full material dataclass
+```
+
 # How to install
 ## Using pip
 ```bash
@@ -56,8 +72,8 @@ pip install python-materialsdb
 ```
 
 # Dependencies
-* [lxml][2] (BSD) : xml parser
-* [ifcopenshell][3] (LGPL) : ifc read/write
+* [lxml][2] (BSD) : xml parser (tested with version 6.1.1)
+* [ifcopenshell][3] (LGPL) : ifc read/write (tested with version 0.8.5)
 
 # Third parties :
 * [materialsdb.org][1] (GPL) : materials schema
@@ -65,4 +81,3 @@ pip install python-materialsdb
 [1]: http://www.materialsdb.org
 [2]: https://lxml.de
 [3]: ifcopenshell.org
-

{python-materialsdb-0.0.1 → python_materialsdb-0.1.0}/README.md

@@ -25,9 +25,21 @@ Note: in materialsdb standard languages are [ISO 639-1](https://en.wikipedia.org
 
 # Usage examples :
 Check out some [examples](examples):
-* [Convert lastest materials data to ifc](examples/generate_ifc_project_libraries.py)
+* [Convert latest materials data to ifc](examples/generate_ifc_project_libraries.py)
 * [Create your own materialsdb.org compliant XML](examples/create_layers.py)
 
+# Querying materials :
+The library keeps an sqlite index of the cached materials data for fast
+filtering and single-material access:
+
+```python
+from materialsdb import query
+
+query.refresh()                                   # incremental update from cached xml
+rows = query.search("isolant", sort="lambda")     # filtered, sorted summaries
+material = query.get_material(rows[0].id)         # full material dataclass
+```
+
 # How to install
 ## Using pip
 ```bash
@@ -35,8 +47,8 @@ pip install python-materialsdb
 ```
 
 # Dependencies
-* [lxml][2] (BSD) : xml parser
-* [ifcopenshell][3] (LGPL) : ifc read/write
+* [lxml][2] (BSD) : xml parser (tested with version 6.1.1)
+* [ifcopenshell][3] (LGPL) : ifc read/write (tested with version 0.8.5)
 
 # Third parties :
 * [materialsdb.org][1] (GPL) : materials schema

{python-materialsdb-0.0.1 → python_materialsdb-0.1.0}/pyproject.toml

@@ -7,4 +7,8 @@ build-backend = "setuptools.build_meta"
 [tool.pytest.ini_options]
 testpaths = [
     "tests",
-]
+]
+markers = [
+    "benchmark: performance benchmarks (deselected by default)",
+]
+addopts = "-m 'not benchmark'"

{python-materialsdb-0.0.1 → python_materialsdb-0.1.0}/setup.cfg

@@ -1,6 +1,6 @@
 [metadata]
 name = python-materialsdb
-version = 0.0.1
+version = 0.1.0
 author = Cyril Waechter
 author_email = cyrwae@hotmail.com
 description = A library to work with materialsdb.org open standard for building materials.
@@ -35,6 +35,7 @@ where = src
 
 [options.extras_require]
 ifc = ifcopenshell
+dev = pytest-benchmark
 
 [egg_info]
 tag_build = 

{python-materialsdb-0.0.1 → python_materialsdb-0.1.0}/src/materialsdb/cache.py

@@ -1,10 +1,14 @@
 import os
 import pathlib
 import urllib.request
+from collections import namedtuple
 from typing import Optional
 from lxml import etree
 
-MATERIALSDBINDEXURL = "http://www.materialsdb.org/download/ProducerIndex.xml"
+MATERIALSDBINDEXURLLIST = [
+    "http://www.materialsdb.org/download/ProducerIndex.xml",
+    "http://www.materialsdb.org/download/generic/GenericIndex.xml",
+]
 
 
 def get_cache_folder():
@@ -19,12 +23,12 @@ def get_cache_folder():
     return cache_dir
 
 
-def get_cached_index_path() -> pathlib.Path:
-    return get_cache_folder() / "ProducerIndex.xml"
+def get_cached_index_path(index) -> pathlib.Path:
+    return get_cache_folder() / pathlib.Path(index).name
 
 
-def parse_cached_index() -> etree._ElementTree:
-    path = get_cached_index_path()
+def parse_cached_index(index) -> etree._ElementTree:
+    path = get_cached_index_path(index)
     if path.exists():
         return etree.parse(str(path))
     root = etree.Element("root")
@@ -53,27 +57,48 @@ def get_producers_dir() -> pathlib.Path:
     return producer_path
 
 
-def update_producers_data():
-    cached_index = parse_cached_index()
+Report = namedtuple("Report", ["existing", "updated", "deleted"])
+
+
+def update_producers_data(url_list=MATERIALSDBINDEXURLLIST):
+    existing = []
+    updated = []
+    deleted = []
+    for index in url_list:
+        report = update_producers_from_index(index)
+        existing.extend(report.existing)
+        updated.extend(report.updated)
+        deleted.extend(report.deleted)
+    return Report(existing, updated, deleted)
+
+
+def update_producers_from_index(index):
+    cached_index = parse_cached_index(index)
     cached_root = cached_index.getroot()
-    new_index = etree.parse(MATERIALSDBINDEXURL)
+    with urllib.request.urlopen(index) as response:
+        new_index = etree.parse(response)
     new_root = new_index.getroot()
     producers_dir = get_producers_dir()
     has_index_update = False
+    existing = []
+    updated = []
+    deleted = []
     for company in new_root:
-        cached_company = get_by_id(cached_root, company.get("id"))
-        if (
-            not require_update(cached_company, company)
-            and (producers_dir / pathlib.Path(company.get("href")).name).exists()
-        ):
+        cached_producer = get_by_id(cached_root, company.get("id"))
+        producer_path = producers_dir / pathlib.Path(company.get("href")).name
+        if not require_update(cached_producer, company) and producer_path.exists():
+            existing.append(producer_path)
             continue
-        if cached_company:
-            (producers_dir / pathlib.Path(cached_company.get("href")).name).unlink(True)
+        if cached_producer:
+            cached_path = producers_dir / pathlib.Path(cached_producer.get("href")).name
+            deleted.append(cached_path)
+            cached_path.unlink(True)
         has_index_update = True
-        producer_path = producers_dir / pathlib.Path(company.get("href")).name
         urllib.request.urlretrieve(company.get("href"), producer_path)
+        updated.append(producer_path)
     if has_index_update:
-        new_index.write(str(get_cached_index_path()))
+        new_index.write(str(get_cached_index_path(index)))
+    return Report(existing, updated, deleted)
 
 
 def producers():