py-data-engine 0.3.3__tar.gz → 0.3.4__tar.gz

{py_data_engine-0.3.3/src/py_data_engine.egg-info → py_data_engine-0.3.4}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: py-data-engine
-Version: 0.3.3
+Version: 0.3.4
 Summary: GUI orchestrator for python-based dataframe transform pipelines.
 Author: Data Engine contributors
 License-Expression: MIT
@@ -198,7 +198,7 @@ Data Engine discovers workspaces from a collection root resolved from:
 Each immediate child folder containing `flow_modules/` is treated as a workspace, for example:
 
 - `workspaces/example_workspace/flow_modules/`
-- `workspaces/claims2/flow_modules/`
+- `workspaces/docs2/flow_modules/`
 
 Shared workspace state lives inside each authored workspace:
 
@@ -218,7 +218,7 @@ from data_engine import Flow
 import polars as pl
 
 
-def read_claims(context):
+def read_docs(context):
     return pl.read_excel(context.source.path)
 
 
@@ -234,16 +234,16 @@ def write_parquet(context):
 
 def build():
     return (
-        Flow(group="Claims")
+        Flow(group="Docs")
         .watch(
             mode="poll",
-            source="../../../example_data/Input/claims_flat",
+            source="../../../example_data/Input/docs_flat",
             interval="5s",
             extensions=[".xlsx", ".xls", ".xlsm"],
             settle=1,
         )
         .mirror(root="../../../example_data/Output/example_mirror")
-        .step(read_claims, save_as="raw_df")
+        .step(read_docs, save_as="raw_df")
         .step(keep_open, use="raw_df", save_as="filtered_df")
         .step(write_parquet, use="filtered_df")
     )
@@ -288,8 +288,8 @@ def validate_workbook(context, file_ref):
 
 def build():
     return (
-        Flow(group="Claims")
-        .watch(mode="schedule", run_as="batch", interval="15m", source="../../../example_data/Input/claims_flat")
+        Flow(group="Docs")
+        .watch(mode="schedule", run_as="batch", interval="15m", source="../../../example_data/Input/docs_flat")
         .collect([".xlsx"])
         .map(validate_workbook)
     )
@@ -344,8 +344,8 @@ Useful mirror helpers:
 
 - `context.mirror.with_extension(".parquet")`
 - `context.mirror.with_suffix(".parquet")`
-- `context.mirror.file("open_claims.parquet")`
-- `context.mirror.namespaced_file("open_claims.parquet")`
+- `context.mirror.file("open_docs.parquet")`
+- `context.mirror.namespaced_file("open_docs.parquet")`
 
 `use="name"` loads `context.objects["name"]` into `context.current` before the step runs. `save_as="name"` stores the returned value into `context.objects["name"]`.
 
@@ -356,7 +356,7 @@ The app includes a dataframe-first debug pane for saved parquet artifacts.
 From a flow step, save a debug dataframe with:
 
 ```python
-context.debug.save_frame(context.current, name="raw_claims")
+context.debug.save_frame(context.current, name="raw_docs")
 ```
 
 That writes:
@@ -418,7 +418,7 @@ The runtime loads discovered flows from those compiled modules.
 Generate local smoke data with:
 
 ```bash
-python scripts/generate_smoke_data.py --root . --workspace-id example_workspace --workspace-id claims2
+python scripts/generate_smoke_data.py --root . --workspace-id example_workspace --workspace-id docs2
 ```
 
 Generated local data and workspaces are intentionally ignored:

{py_data_engine-0.3.3 → py_data_engine-0.3.4}/README.md

@@ -127,7 +127,7 @@ Data Engine discovers workspaces from a collection root resolved from:
 Each immediate child folder containing `flow_modules/` is treated as a workspace, for example:
 
 - `workspaces/example_workspace/flow_modules/`
-- `workspaces/claims2/flow_modules/`
+- `workspaces/docs2/flow_modules/`
 
 Shared workspace state lives inside each authored workspace:
 
@@ -147,7 +147,7 @@ from data_engine import Flow
 import polars as pl
 
 
-def read_claims(context):
+def read_docs(context):
     return pl.read_excel(context.source.path)
 
 
@@ -163,16 +163,16 @@ def write_parquet(context):
 
 def build():
     return (
-        Flow(group="Claims")
+        Flow(group="Docs")
         .watch(
             mode="poll",
-            source="../../../example_data/Input/claims_flat",
+            source="../../../example_data/Input/docs_flat",
             interval="5s",
             extensions=[".xlsx", ".xls", ".xlsm"],
             settle=1,
         )
         .mirror(root="../../../example_data/Output/example_mirror")
-        .step(read_claims, save_as="raw_df")
+        .step(read_docs, save_as="raw_df")
         .step(keep_open, use="raw_df", save_as="filtered_df")
         .step(write_parquet, use="filtered_df")
     )
@@ -217,8 +217,8 @@ def validate_workbook(context, file_ref):
 
 def build():
     return (
-        Flow(group="Claims")
-        .watch(mode="schedule", run_as="batch", interval="15m", source="../../../example_data/Input/claims_flat")
+        Flow(group="Docs")
+        .watch(mode="schedule", run_as="batch", interval="15m", source="../../../example_data/Input/docs_flat")
         .collect([".xlsx"])
         .map(validate_workbook)
     )
@@ -273,8 +273,8 @@ Useful mirror helpers:
 
 - `context.mirror.with_extension(".parquet")`
 - `context.mirror.with_suffix(".parquet")`
-- `context.mirror.file("open_claims.parquet")`
-- `context.mirror.namespaced_file("open_claims.parquet")`
+- `context.mirror.file("open_docs.parquet")`
+- `context.mirror.namespaced_file("open_docs.parquet")`
 
 `use="name"` loads `context.objects["name"]` into `context.current` before the step runs. `save_as="name"` stores the returned value into `context.objects["name"]`.
 
@@ -285,7 +285,7 @@ The app includes a dataframe-first debug pane for saved parquet artifacts.
 From a flow step, save a debug dataframe with:
 
 ```python
-context.debug.save_frame(context.current, name="raw_claims")
+context.debug.save_frame(context.current, name="raw_docs")
 ```
 
 That writes:
@@ -347,7 +347,7 @@ The runtime loads discovered flows from those compiled modules.
 Generate local smoke data with:
 
 ```bash
-python scripts/generate_smoke_data.py --root . --workspace-id example_workspace --workspace-id claims2
+python scripts/generate_smoke_data.py --root . --workspace-id example_workspace --workspace-id docs2
 ```
 
 Generated local data and workspaces are intentionally ignored:

{py_data_engine-0.3.3 → py_data_engine-0.3.4}/src/data_engine/core/flow.py

@@ -37,7 +37,7 @@ class Flow:
         from data_engine import Flow
 
         flow = (
-            Flow(group="Claims")
+            Flow(group="Docs")
             .watch(mode="poll", source="incoming", interval="30s", extensions=[".xlsx"])
             .mirror(root="processed")
         )
@@ -112,9 +112,9 @@ class Flow:
 
             from data_engine import Flow
 
-            manual_flow = Flow(group="Claims").watch(mode="manual")
-            poll_flow = Flow(group="Claims").watch(mode="poll", source="incoming", interval="5s")
-            schedule_flow = Flow(group="Claims").watch(mode="schedule", interval="15m")
+            manual_flow = Flow(group="Docs").watch(mode="manual")
+            poll_flow = Flow(group="Docs").watch(mode="poll", source="incoming", interval="5s")
+            schedule_flow = Flow(group="Docs").watch(mode="schedule", interval="15m")
 
             assert manual_flow.mode == "manual"
             assert poll_flow.mode == "poll"
@@ -248,7 +248,7 @@ class Flow:
 
             from data_engine import Flow
 
-            flow = Flow(group="Claims").mirror(root="processed")
+            flow = Flow(group="Docs").mirror(root="processed")
 
             assert str(flow.mirror_spec.root).endswith("processed")
 
@@ -286,10 +286,10 @@ class Flow:
 
             from data_engine import Flow
 
-            def read_claims(context):
+            def read_docs(context):
                 return context.current
 
-            flow = Flow(group="Claims").step(read_claims, save_as="raw_df")
+            flow = Flow(group="Docs").step(read_docs, save_as="raw_df")
 
             assert flow.steps[0].save_as == "raw_df"
 
@@ -357,7 +357,7 @@ class Flow:
             def summarize(file_ref):
                 return file_ref.name
 
-            flow = Flow(group="Claims").collect(extensions=[".xlsx"]).map(fn=summarize)
+            flow = Flow(group="Docs").collect(extensions=[".xlsx"]).map(fn=summarize)
 
             assert len(flow.steps) == 2
 

{py_data_engine-0.3.3 → py_data_engine-0.3.4}/src/data_engine/core/primitives.py

@@ -348,7 +348,7 @@ class FlowContext:
 
         from data_engine.core.primitives import FlowContext
 
-        context = FlowContext(flow_name="claims", group="Claims", current=1)
+        context = FlowContext(flow_name="docs", group="Docs", current=1)
         context.objects["raw"] = context.current
 
         assert context.current == 1
@@ -389,7 +389,7 @@ class FlowContext:
         ----------
         name : str | Path
             Relative database file name, such as ``"analytics.duckdb"`` or
-            ``"claims/analytics.duckdb"``.
+            ``"docs/analytics.duckdb"``.
 
         Returns
         -------