:arrow_up better custom line items support (#182)

docs/guide/custom_v1.md → docs/extras/guide/custom_v1.md

@@ -85,6 +85,53 @@ print(str(result.document.inference.prediction.fields["my-field"]))
 print(str(result.document.inference.prediction.classifications["my-classification"]))
 ```
 
+
+# 🧪 Custom Line Items
+
+> **⚠️ Warning**: Custom Line Items are an **experimental** feature, results may vary.
+
+
+Though not supported directly in the API, sometimes you might need to reconstitute line items by hand.
+The library provides a tool for this very purpose:
+
+## columns_to_line_items()
+The **columns_to_line_items()** function can be called from the document and page level prediction objects.
+
+It takes the following arguments:
+
+* **anchor_names** (`List[str]`): a list of the names of possible anchor (field) candidate for the horizontal placement a line. If all provided anchors are invalid, the `LineItemV1` won't be built.
+* **field_names** (`List[str]`): a list of fields to retrieve the values from
+* **height_tolerance** (`float`): Optional, the height tolerance used to build the line. It helps when the height of a line can vary unexpectedly.
+
+Example use:
+
+```python
+# document-level
+response.document.inference.prediction.columns_to_line_items(
+  anchor_names,
+  field_names,
+  0.011 # optional, defaults to 0.01
+)
+
+# page-level
+response.document.pages[0].prediction.columns_to_line_items(
+    anchor_names,
+    field_names,
+    0.011 # optional, defaults to 0.01
+)
+```
+
+It returns a list of [CustomLineV1](#CustomlineV1) objects.
+
+## CustomlineV1
+
+`CustomlineV1` represents a line as it has been read from column fields. It has the following attributes:
+
+* **row_number** (`int`): Number of a given line. Starts at 1.
+* **fields** (`Dict[str, ListFieldValueV1]`[]): List of the fields associated with the line, indexed by their column name.
+* **bbox** (`BBox`): Simple bounding box of the current line representing the 4 minimum & maximum coordinates as `float` values.
+
+
 # Questions?
 
 [Join our Slack](https://join.slack.com/t/mindee-community/shared_invite/zt-1jv6nawjq-FDgFcF2T5CmMmRpl9LLptw)

examples/custom_line_items_reconstruction.py

@@ -0,0 +1,55 @@
+import os
+
+from mindee import Client, product
+from mindee.parsing.common.predict_response import PredictResponse
+
+CUSTOM_ENDPOINT_NAME = os.getenv("CUSTOM_ENDPOINT_NAME", "my-endpoint-name")
+CUSTOM_ACCOUNT_NAME = os.getenv("CUSTOM_ACCOUNT_NAME", "my-account-name")
+CUSTOM_VERSION = os.getenv("CUSTOM_VERSION", "1")
+CUSTOM_DOCUMENT_PATH = os.getenv("CUSTOM_DOCUMENT_PATH", "path/to/your/file.ext")
+
+# This example assumes you are following the associated tutorial:
+# https://developers.mindee.com/docs/extracting-line-items-tutorial#line-reconstruction-code
+anchors = ["category"]
+columns = ["category", "previous_year_actual", "year_actual", "year_projection"]
+
+
+def get_field_content(line, field) -> str:
+    if field in line.fields:
+        return str(line.fields[field].content)
+    return ""
+
+
+def print_line(line) -> None:
+    category = get_field_content(line, "category")
+    previous_year_actual = get_field_content(line, "previous_year_actual")
+    year_actual = get_field_content(line, "year_actual")
+    year_projection = get_field_content(line, "year_projection")
+    # here ljust() fills the rest of the given size with spaces
+    string_line = (
+        category.ljust(20, " ")
+        + previous_year_actual.ljust(10, " ")
+        + year_projection.ljust(10, " ")
+        + year_actual
+    )
+
+    print(string_line)
+
+
+client = Client()
+
+custom_endpoint = client.create_endpoint(
+    CUSTOM_ENDPOINT_NAME, CUSTOM_ACCOUNT_NAME, CUSTOM_VERSION
+)
+input_doc = client.source_from_path(CUSTOM_DOCUMENT_PATH)
+
+
+response: PredictResponse[product.CustomV1] = client.parse(
+    product.CustomV1, input_doc, endpoint=custom_endpoint
+)
+line_items = response.document.inference.prediction.columns_to_line_items(
+    anchors, columns
+)
+
+for line in line_items:
+    print_line(line)

mindee/geometry/bbox.py

@@ -43,3 +43,31 @@ def get_bbox(points: Points) -> BBox:
     x_min = min(v[0] for v in points)
     x_max = max(v[0] for v in points)
     return BBox(x_min, y_min, x_max, y_max)
+
+
+def merge_bbox(bbox_1: BBox, bbox_2: BBox) -> BBox:
+    """Merges two BBox."""
+    return BBox(
+        min(bbox_1.x_min, bbox_2.x_min),
+        min(bbox_1.y_min, bbox_2.y_min),
+        max(bbox_1.x_max, bbox_2.x_max),
+        max(bbox_1.y_max, bbox_2.y_max),
+    )
+
+
+def extend_bbox(bbox: BBox, points: Points) -> BBox:
+    """
+    Given a BBox and a sequence of points, calculate the surrounding bbox that encompasses all.
+
+    :param bbox: initial BBox to extend.
+    :param points: Sequence of points to process. Accepts polygons and similar
+    """
+    all_points = []
+    for point in points:
+        all_points.append(point)
+
+    y_min = min(v[1] for v in all_points)
+    y_max = max(v[1] for v in all_points)
+    x_min = min(v[0] for v in all_points)
+    x_max = max(v[0] for v in all_points)
+    return merge_bbox(bbox, BBox(x_min, y_min, x_max, y_max))

mindee/geometry/quadrilateral.py

@@ -24,22 +24,6 @@ def centroid(self) -> Point:
         return get_centroid(self)
 
 
-def get_bounding_box(points: Points) -> Quadrilateral:
-    """
-    Given a sequence of points, calculate a bounding box that encompasses all points.
-
-    :param points: Polygon to process.
-    :return: A bounding box that encompasses all points.
-    """
-    x_min, y_min, x_max, y_max = get_bbox(points)
-    return Quadrilateral(
-        Point(x_min, y_min),
-        Point(x_max, y_min),
-        Point(x_max, y_max),
-        Point(x_min, y_max),
-    )
-
-
 def quadrilateral_from_prediction(prediction: Sequence[list]) -> Quadrilateral:
     """
     Transform a prediction into a Quadrilateral.
@@ -54,3 +38,19 @@ def quadrilateral_from_prediction(prediction: Sequence[list]) -> Quadrilateral:
         Point(prediction[2][0], prediction[2][1]),
         Point(prediction[3][0], prediction[3][1]),
     )
+
+
+def get_bounding_box(points: Points) -> Quadrilateral:
+    """
+    Given a sequence of points, calculate a bounding box that encompasses all points.
+
+    :param points: Polygon to process.
+    :return: A bounding box that encompasses all points.
+    """
+    x_min, y_min, x_max, y_max = get_bbox(points)
+    return Quadrilateral(
+        Point(x_min, y_min),
+        Point(x_max, y_min),
+        Point(x_max, y_max),
+        Point(x_min, y_max),
+    )

mindee/parsing/custom/__init__.py

@@ -1,3 +1,3 @@
 from mindee.parsing.custom.classification import ClassificationFieldV1
-from mindee.parsing.custom.line_items import LineV1, get_line_items
+from mindee.parsing.custom.line_items import CustomLineV1, get_line_items
 from mindee.parsing.custom.list import ListFieldV1, ListFieldValueV1