diff --git a/PKG-INFO b/PKG-INFO
index 9c87cc02c1f691d197d9c360ffea667dc9a35977..8afa9731644afd7cb3d175b5c5735c4eee8aae86 100644
--- a/PKG-INFO
+++ b/PKG-INFO
@@ -1,6 +1,6 @@
Metadata-Version: 1.0
Name: swh.model
-Version: 0.0.22
+Version: 0.0.23
Summary: Software Heritage data model
Home-page: https://forge.softwareheritage.org/diffusion/DMOD/
Author: Software Heritage developers
diff --git a/docs/data-model.rst b/docs/data-model.rst
index 1693ae496545272e794cf19cea3f6bf9ef854479..f6e4f066a0ffb589d49593163367a41788e755af 100644
--- a/docs/data-model.rst
+++ b/docs/data-model.rst
@@ -3,11 +3,11 @@
Data model
==========
-TODO
-
-Lorem ipsum dolor sit amet, consectetur adipiscing elit, sed do eiusmod tempor
-incididunt ut labore et dolore magna aliqua. Ut enim ad minim veniam, quis
-nostrud exercitation ullamco laboris nisi ut aliquip ex ea commodo
-consequat. Duis aute irure dolor in reprehenderit in voluptate velit esse
-cillum dolore eu fugiat nulla pariatur. Excepteur sint occaecat cupidatat non
-proident, sunt in culpa qui officia deserunt mollit anim id est laborum.
+.. _swh-merkle-dag:
+.. figure:: images/swh-merkle-dag.svg
+ :width: 1024px
+ :align: center
+
+ Software Heritage archive as a Merkle DAG, augmented with crawling
+ information (click to zoom).
+
diff --git a/docs/images/.gitignore b/docs/images/.gitignore
new file mode 100644
index 0000000000000000000000000000000000000000..e9c694ce24364021872ec307b95ca435d82b0aff
--- /dev/null
+++ b/docs/images/.gitignore
@@ -0,0 +1,2 @@
+swh-merkle-dag.pdf
+swh-merkle-dag.svg
diff --git a/docs/images/Makefile b/docs/images/Makefile
new file mode 100644
index 0000000000000000000000000000000000000000..2bc794e965ba7be048c00263d49e6a8c0769a5b5
--- /dev/null
+++ b/docs/images/Makefile
@@ -0,0 +1,25 @@
+
+MERKLE_DAG = swh-merkle-dag.pdf swh-merkle-dag.svg
+
+BUILD_TARGETS =
+BUILD_TARGETS += $(MERKLE_DAG)
+
+all: $(BUILD_TARGETS)
+
+
+# dia exporters
+
+%.eps: %.dia
+ dia -t eps --export $@ $<
+
+%.svg: %.dia
+ dia -t svg --export $@ $<
+
+# generic converters
+
+%.pdf: %.eps
+ epstopdf $<
+
+
+clean:
+ -rm -f $(BUILD_TARGETS)
diff --git a/docs/images/swh-merkle-dag.dia b/docs/images/swh-merkle-dag.dia
new file mode 100644
index 0000000000000000000000000000000000000000..00edd643bf62df4f65766dcfaaf96be5611ea25b
Binary files /dev/null and b/docs/images/swh-merkle-dag.dia differ
diff --git a/swh.model.egg-info/PKG-INFO b/swh.model.egg-info/PKG-INFO
index 9c87cc02c1f691d197d9c360ffea667dc9a35977..8afa9731644afd7cb3d175b5c5735c4eee8aae86 100644
--- a/swh.model.egg-info/PKG-INFO
+++ b/swh.model.egg-info/PKG-INFO
@@ -1,6 +1,6 @@
Metadata-Version: 1.0
Name: swh.model
-Version: 0.0.22
+Version: 0.0.23
Summary: Software Heritage data model
Home-page: https://forge.softwareheritage.org/diffusion/DMOD/
Author: Software Heritage developers
diff --git a/swh.model.egg-info/SOURCES.txt b/swh.model.egg-info/SOURCES.txt
index b45f730dce555fb482c6a30a86be695e9ed496b6..4b2269ff4fe5c7dfd1b6889241146897135bb07b 100644
--- a/swh.model.egg-info/SOURCES.txt
+++ b/swh.model.egg-info/SOURCES.txt
@@ -26,6 +26,9 @@ docs/index.rst
docs/persistent-identifiers.rst
docs/_static/.placeholder
docs/_templates/.placeholder
+docs/images/.gitignore
+docs/images/Makefile
+docs/images/swh-merkle-dag.dia
swh/__init__.py
swh.model.egg-info/PKG-INFO
swh.model.egg-info/SOURCES.txt
diff --git a/swh/model/identifiers.py b/swh/model/identifiers.py
index 51d2d2e9b6f94467b526ef6291bc1f76d79b8202..eef7710698e0ec499a62e85e1a507a9371f8fcf5 100644
--- a/swh/model/identifiers.py
+++ b/swh/model/identifiers.py
@@ -538,7 +538,7 @@ def snapshot_identifier(snapshot, *, ignore_unresolved=False):
- the branch name (as raw bytes)
- a null byte (``\\x00``)
- the length of the target identifier, as an ascii-encoded decimal number
- (``20`` for current intrinisic identifiers, ``0`` for dangling
+ (``20`` for current intrinsic identifiers, ``0`` for dangling
branches, the length of the target branch name for branch aliases)
- a colon (``:``)
- the identifier of the target object pointed at by the branch,
@@ -638,18 +638,35 @@ def persistent_identifier(type, object, version=1):
PERSISTENT_IDENTIFIER_KEYS = [
- 'namespace', 'scheme_version', 'object_type', 'object_id']
+ 'namespace', 'scheme_version', 'object_type', 'object_id', 'metadata']
+
+PERSISTENT_IDENTIFIER_PARTS_SEP = ';'
def parse_persistent_identifier(persistent_id):
- """Parse swh's persistent identifier scheme.
+ """Parse swh's :ref:`persistent-identifiers` scheme.
Args:
persistent_id (str): A persistent identifier
Returns:
- dict with keys namespace, scheme_version, object_type, object_id
+ dict: dict with keys :
+
+ * namespace, holding str value
+ * scheme_version, holding str value
+ * object_type, holding str value
+ * object_id, holding str value
+ * metadata, holding dict value
"""
- data = persistent_id.split(':')
+ persistent_id_parts = persistent_id.split(PERSISTENT_IDENTIFIER_PARTS_SEP)
+ data = persistent_id_parts.pop(0).split(':')
+ persistent_id_metadata = {}
+ for part in persistent_id_parts:
+ try:
+ key, val = part.split('=')
+ persistent_id_metadata[key] = val
+ except Exception:
+ pass
+ data.append(persistent_id_metadata)
return dict(zip(PERSISTENT_IDENTIFIER_KEYS, data))
diff --git a/swh/model/tests/test_identifiers.py b/swh/model/tests/test_identifiers.py
index 26dc01e98543557197926ac41da6733d8de786ff..afe943b6de8699ffb1775c8df135253c3a1d1a42 100644
--- a/swh/model/tests/test_identifiers.py
+++ b/swh/model/tests/test_identifiers.py
@@ -818,6 +818,32 @@ class SnapshotIdentifier(unittest.TestCase):
'scheme_version': _version,
'object_type': _type,
'object_id': _hash,
+ 'metadata': {}
+ }
+ actual_result = identifiers.parse_persistent_identifier(pid)
+ self.assertEquals(actual_result, expected_result)
+
+ for pid, _type, _version, _hash, _metadata in [
+ ('swh:1:cnt:9c95815d9e9d91b8dae8e05d8bbc696fe19f796b;lines=1-18;origin=https://github.com/python/cpython', # noqa
+ 'cnt', '1', '9c95815d9e9d91b8dae8e05d8bbc696fe19f796b',
+ {
+ 'lines': '1-18',
+ 'origin': 'https://github.com/python/cpython'
+ }),
+ ('swh:1:dir:0b6959356d30f1a4e9b7f6bca59b9a336464c03d;origin=deb://Debian/packages/linuxdoc-tools', # noqa
+ 'dir', '1', '0b6959356d30f1a4e9b7f6bca59b9a336464c03d',
+ {
+ 'origin': 'deb://Debian/packages/linuxdoc-tools'
+ }),
+ ('swh:1:dir:0b6959356d30f1a4e9b7f6bca59b9a336464c03d;invalid;malformed', # noqa
+ 'dir', '1', '0b6959356d30f1a4e9b7f6bca59b9a336464c03d', {})
+ ]:
+ expected_result = {
+ 'namespace': 'swh',
+ 'scheme_version': _version,
+ 'object_type': _type,
+ 'object_id': _hash,
+ 'metadata': _metadata
}
actual_result = identifiers.parse_persistent_identifier(pid)
self.assertEquals(actual_result, expected_result)
diff --git a/version.txt b/version.txt
index 3a338cb2e577d69dc9a1844e049bfc834a93a7e7..c0bdf11c06ccb6f33f80e32ef7f296cd2080242e 100644
--- a/version.txt
+++ b/version.txt
@@ -1 +1 @@
-v0.0.22-0-ga06122e
\ No newline at end of file
+v0.0.23-0-g448eafa
\ No newline at end of file