repo: Rename to record

Fixes: #361
Fixes: #393

Author: 0dust

CHANGELOG.md

@@ -10,6 +10,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 - Notes on development dependencies in `setup.py` files to codebase notes.
 - Test for `cached_download`
 ### Changed
+- `repo`/`Repo` to `record`/`Record`
 - Definitions with a `spec` can use the `subspec` parameter to declare that they
   are a list or a dict where the values are of the `spec` type. Rather than the
   list or dict itself being of the `spec` type.

dffml/cli/cli.py

@@ -7,7 +7,7 @@
 import pkg_resources
 
 from ..version import VERSION
-from ..repo import Repo
+from ..record import Record
 from ..source.source import BaseSource
 from ..util.packaging import is_develop
 from ..util.cli.arg import Arg
@@ -37,40 +37,42 @@ async def run(self):
 
 class Edit(SourcesCMD, KeysCMD):
     """
-    Edit each specified repo
+    Edit each specified record
     """
 
     async def run(self):
         async with self.sources as sources:
             async with sources() as sctx:
                 for key in self.keys:
-                    repo = await sctx.repo(key)
+                    record = await sctx.record(key)
                     pdb.set_trace()
-                    await sctx.update(repo)
+                    await sctx.update(record)
 
 
 class Merge(CMD):
     """
-    Merge repo data between sources
+    Merge record data between sources
     """
 
     arg_dest = Arg(
-        "dest", help="Sources merge repos into", type=BaseSource.load_labeled
+        "dest", help="Sources merge records into", type=BaseSource.load_labeled
     )
     arg_src = Arg(
-        "src", help="Sources to pull repos from", type=BaseSource.load_labeled
+        "src",
+        help="Sources to pull records from",
+        type=BaseSource.load_labeled,
     )
 
     async def run(self):
         async with self.src.withconfig(
             self.extra_config
         ) as src, self.dest.withconfig(self.extra_config) as dest:
             async with src() as sctx, dest() as dctx:
-                async for src in sctx.repos():
-                    repo = Repo(src.key)
-                    repo.merge(src)
-                    repo.merge(await dctx.repo(repo.key))
-                    await dctx.update(repo)
+                async for src in sctx.records():
+                    record = Record(src.key)
+                    record.merge(src)
+                    record.merge(await dctx.record(record.key))
+                    await dctx.update(record)
 
 
 class ImportExportCMD(PortCMD, SourcesCMD):
@@ -80,7 +82,7 @@ class ImportExportCMD(PortCMD, SourcesCMD):
 
 
 class Import(ImportExportCMD):
-    """Imports repos"""
+    """Imports records"""
 
     async def run(self):
         async with self.sources as sources:
@@ -89,7 +91,7 @@ async def run(self):
 
 
 class Export(ImportExportCMD):
-    """Exports repos"""
+    """Exports records"""
 
     async def run(self):
         async with self.sources as sources:

dffml/cli/dataflow.py

@@ -97,14 +97,14 @@ class RunCMD(SourcesCMD):
     arg_sources = SourcesCMD.arg_sources.modify(required=False)
     arg_caching = Arg(
         "-caching",
-        help="Skip running DataFlow if a repo already contains these features",
+        help="Skip running DataFlow if a record already contains these features",
         nargs="+",
         required=False,
         default=[],
     )
     arg_no_update = Arg(
         "-no-update",
-        help="Update repo with sources",
+        help="Update record with sources",
         required=False,
         default=False,
         action="store_true",
@@ -134,42 +134,42 @@ class RunCMD(SourcesCMD):
         nargs="+",
         action=ParseInputsAction,
         default=[],
-        help="Other inputs to add under each ctx (repo's key will "
+        help="Other inputs to add under each ctx (record's key will "
         + "be used as the context)",
     )
-    arg_repo_def = Arg(
-        "-repo-def",
+    arg_record_def = Arg(
+        "-record-def",
         default=False,
         type=str,
-        help="Definition to be used for repo.key."
-        + "If set, repo.key will be added to the set of inputs "
-        + "under each context (which is also the repo's key)",
+        help="Definition to be used for record.key."
+        + "If set, record.key will be added to the set of inputs "
+        + "under each context (which is also the record's key)",
     )
 
     def __init__(self, *args, **kwargs):
         super().__init__(*args, **kwargs)
         self.orchestrator = self.orchestrator.withconfig(self.extra_config)
 
 
-class RunAllRepos(RunCMD):
-    """Run dataflow for all repos in sources"""
+class RunAllRecords(RunCMD):
+    """Run dataflow for all records in sources"""
 
-    async def repos(self, sctx):
+    async def records(self, sctx):
         """
-        This method exists so that it can be overriden by RunRepoSet
+        This method exists so that it can be overriden by RunRecordSet
         """
-        async for repo in sctx.repos():
-            yield repo
+        async for record in sctx.records():
+            yield record
 
     async def run_dataflow(self, orchestrator, sources, dataflow):
         # Orchestrate the running of these operations
         async with orchestrator(dataflow) as octx, sources() as sctx:
             # Add our inputs to the input network with the context being the
-            # repo key
+            # record key
             inputs = []
-            async for repo in self.repos(sctx):
-                # Skip running DataFlow if repo already has features
-                existing_features = repo.features()
+            async for record in self.records(sctx):
+                # Skip running DataFlow if record already has features
+                existing_features = record.features()
                 if self.caching and all(
                     map(
                         lambda cached: cached in existing_features,
@@ -178,19 +178,19 @@ async def run_dataflow(self, orchestrator, sources, dataflow):
                 ):
                     continue
 
-                repo_inputs = []
+                record_inputs = []
                 for value, def_name in self.inputs:
-                    repo_inputs.append(
+                    record_inputs.append(
                         Input(
                             value=value,
                             definition=dataflow.definitions[def_name],
                         )
                     )
-                if self.repo_def:
-                    repo_inputs.append(
+                if self.record_def:
+                    record_inputs.append(
                         Input(
-                            value=repo.key,
-                            definition=dataflow.definitions[self.repo_def],
+                            value=record.key,
+                            definition=dataflow.definitions[self.record_def],
                         )
                     )
 
@@ -199,8 +199,8 @@ async def run_dataflow(self, orchestrator, sources, dataflow):
                 inputs.append(
                     MemoryInputSet(
                         MemoryInputSetConfig(
-                            ctx=StringInputSetContext(repo.key),
-                            inputs=repo_inputs,
+                            ctx=StringInputSetContext(record.key),
+                            inputs=record_inputs,
                         )
                     )
                 )
@@ -212,14 +212,14 @@ async def run_dataflow(self, orchestrator, sources, dataflow):
                 *inputs, strict=not self.no_strict
             ):
                 ctx_str = (await ctx.handle()).as_string()
-                # TODO(p4) Make a RepoInputSetContext which would let us
-                # store the repo instead of recalling it by the URL
-                repo = await sctx.repo(ctx_str)
+                # TODO(p4) Make a RecordInputSetContext which would let us
+                # store the record instead of recalling it by the URL
+                record = await sctx.record(ctx_str)
                 # Store the results
-                repo.evaluated(results)
-                yield repo
+                record.evaluated(results)
+                yield record
                 if not self.no_update:
-                    await sctx.update(repo)
+                    await sctx.update(record)
 
     async def run(self):
         dataflow_path = pathlib.Path(self.dataflow)
@@ -232,35 +232,35 @@ async def run(self):
                 exported = await loader.loadb(dataflow_path.read_bytes())
                 dataflow = DataFlow._fromdict(**exported)
         async with self.orchestrator as orchestrator, self.sources as sources:
-            async for repo in self.run_dataflow(
+            async for record in self.run_dataflow(
                 orchestrator, sources, dataflow
             ):
-                yield repo
+                yield record
 
 
-class RunRepoSet(RunAllRepos, KeysCMD):
-    """Run dataflow for single repo or set of repos"""
+class RunRecordSet(RunAllRecords, KeysCMD):
+    """Run dataflow for single record or set of records"""
 
-    async def repos(self, sctx):
+    async def records(self, sctx):
         for key in self.keys:
-            yield await sctx.repo(key)
+            yield await sctx.record(key)
 
     def __init__(self, *args, **kwargs):
         super().__init__(*args, **kwargs)
         self.sources = SubsetSources(*self.sources, keys=self.keys)
 
 
-class RunRepos(CMD):
-    """Run DataFlow and assign output to a repo"""
+class RunRecords(CMD):
+    """Run DataFlow and assign output to a record"""
 
-    _set = RunRepoSet
-    _all = RunAllRepos
+    _set = RunRecordSet
+    _all = RunAllRecords
 
 
 class Run(CMD):
     """Run dataflow"""
 
-    repos = RunRepos
+    records = RunRecords
 
 
 class Diagram(CMD):

dffml/cli/list.py

@@ -6,16 +6,16 @@
 from ..util.cli.cmds import SourcesCMD, ListEntrypoint
 
 
-class ListRepos(SourcesCMD):
+class ListRecords(SourcesCMD):
     """
-    List repos stored in sources
+    List records stored in sources
     """
 
     async def run(self):
         async with self.sources as sources:
             async with sources() as sctx:
-                async for repo in sctx.repos():
-                    print(repo)
+                async for record in sctx.records():
+                    print(record)
 
 
 class ListServices(ListEntrypoint):
@@ -48,10 +48,10 @@ class ListModels(ListEntrypoint):
 
 class List(CMD):
     """
-    List repos and installed interfaces
+    List records and installed interfaces
     """
 
-    repos = ListRepos
+    records = ListRecords
     sources = ListSources
     models = ListModels
     services = ListServices

dffml/cli/ml.py

@@ -38,29 +38,29 @@ class PredictAll(MLCMD):
 
     arg_update = Arg(
         "-update",
-        help="Update repo with sources",
+        help="Update record with sources",
         required=False,
         default=False,
         action="store_true",
     )
 
     async def run(self):
-        async for repo in predict(
-            self.model, self.sources, update=self.update, keep_repo=True
+        async for record in predict(
+            self.model, self.sources, update=self.update, keep_record=True
         ):
-            yield repo
+            yield record
 
 
-class PredictRepo(PredictAll, KeysCMD):
-    """Predictions for individual repos"""
+class PredictRecord(PredictAll, KeysCMD):
+    """Predictions for individual records"""
 
     def __init__(self, *args, **kwargs):
         super().__init__(*args, **kwargs)
         self.sources = SubsetSources(*self.sources, keys=self.keys)
 
 
 class Predict(CMD):
-    """Evaluate features against repos and produce a prediction"""
+    """Evaluate features against records and produce a prediction"""
 
-    repo = PredictRepo
+    record = PredictRecord
     _all = PredictAll

dffml/feature/feature.py

@@ -63,7 +63,7 @@ async def inc(self, key, default=None, by=1):
 
 class Data(Task):
     """
-    Passed to each feature during evaluation. Shared between all features a repo
+    Passed to each feature during evaluation. Shared between all features a record
     is being evaluated with
     """