Add relative param to .crop & err on invalid boxes

Addresses https://github.com/jsvine/pdfplumber/issues/245

Also adds `relative` param to .within_bbox, and adds a new
utils.calculate_area(bbox) method.

README.md

@@ -93,8 +93,8 @@ The `pdfplumber.Page` class is at the core of `pdfplumber`. Most things you'll d
 
 | Method | Description |
 |--------|-------------|
-|`.crop(bounding_box)`| Returns a version of the page cropped to the bounding box, which should be expressed as 4-tuple with the values `(x0, top, x1, bottom)`. Cropped pages retain objects that fall at least partly within the bounding box. If an object falls only partly within the box, its dimensions are sliced to fit the bounding box.|
-|`.within_bbox(bounding_box)`| Similar to `.crop`, but only retains objects that fall *entirely* within the bounding box.|
+|`.crop(bounding_box, relative=False)`| Returns a version of the page cropped to the bounding box, which should be expressed as 4-tuple with the values `(x0, top, x1, bottom)`. Cropped pages retain objects that fall at least partly within the bounding box. If an object falls only partly within the box, its dimensions are sliced to fit the bounding box. If `relative=True`, the bounding box is calculated as an offset from the top-left of the page's bounding box, rather than an absolute positioning.|
+|`.within_bbox(bounding_box, relative=False)`| Similar to `.crop`, but only retains objects that fall *entirely* within the bounding box.|
 |`.filter(test_function)`| Returns a version of the page with only the `.objects` for which `test_function(obj)` returns `True`.|
 |`.extract_text(x_tolerance=3, y_tolerance=3)`| Collates all of the page's character objects into a single string. Adds spaces where the difference between the `x1` of one character and the `x0` of the next is greater than `x_tolerance`. Adds newline characters where the difference between the `doctop` of one character and the `doctop` of the next is greater than `y_tolerance`.|
 |`.extract_words(x_tolerance=3, y_tolerance=3, horizontal_ltr=True, vertical_ttb=True)`| Returns a list of all word-looking things and their bounding boxes. Words are considered to be sequences of characters where (for "upright" characters) the difference between the `x1` of one character and the `x0` of the next is less than or equal to `x_tolerance` *and* where the `doctop` of one character and the `doctop` of the next is less than or equal to `y_tolerance`. A similar approach is taken for non-upright characters, but instead measuring the vertical, rather than horizontal, distances between them. The parameters `horizontal_ltr` and `vertical_ttb` indicate whether the words should be read from left-to-right (for horizontal words) / top-to-bottom (for vertical words).|

pdfplumber/page.py

@@ -236,14 +236,14 @@ class Page(Container):
     def extract_words(self, **kwargs):
         return utils.extract_words(self.chars, **kwargs)
 
-    def crop(self, bbox):
-        return CroppedPage(self, self.decimalize(bbox))
+    def crop(self, bbox, relative=False):
+        return CroppedPage(self, self.decimalize(bbox), relative=relative)
 
-    def within_bbox(self, bbox):
+    def within_bbox(self, bbox, relative=False):
         """
         Same as .crop, except only includes objects fully within the bbox
         """
-        return CroppedPage(self, self.decimalize(bbox), utils.within_bbox)
+        return CroppedPage(self, self.decimalize(bbox), relative=relative, crop_fn=utils.within_bbox)
 
     def filter(self, test_function):
         return FilteredPage(self, test_function)
@@ -280,9 +280,30 @@ class DerivedPage(Page):
             self.root_page = parent_page.root_page
 
 
+def test_proposed_bbox(bbox, parent_bbox):
+    bbox_area = utils.calculate_area(bbox)
+    if bbox_area == 0:
+        raise ValueError(f"Bounding box {bbox} has an area of zero.")
+
+    overlap = utils.get_bbox_overlap(bbox, parent_bbox)
+    overlap_area = utils.calculate_area(overlap)
+    if overlap_area < bbox_area:
+        raise ValueError(
+            f"Bounding box {bbox} is not fully within "
+            f"parent page bounding box {parent_bbox}"
+        )
+
 class CroppedPage(DerivedPage):
-    def __init__(self, parent_page, bbox, crop_fn=utils.crop_to_bbox):
-        self.bbox = bbox
+    def __init__(self, parent_page, bbox, crop_fn=utils.crop_to_bbox, relative=False):
+        if relative:
+            print("Parent page", parent_page.bbox)
+            o_x0, o_top, _, _ = parent_page.bbox
+            x0, top, x1, bottom = bbox
+            self.bbox = (x0 + o_x0, top + o_top, x1 + o_x0, bottom + o_top)
+        else:
+            self.bbox = bbox
+
+        test_proposed_bbox(self.bbox, parent_page.bbox)
         self.crop_fn = crop_fn
         super().__init__(parent_page)
 

pdfplumber/utils.py

@@ -333,6 +333,11 @@ def get_bbox_overlap(a, b):
     else:
         return None
 
+def calculate_area(bbox):
+    left, top, right, bottom = bbox
+    if left > right or top > bottom:
+        raise ValueError(f"{bbox} has a negative width or height.")
+    return (right - left) * (bottom - top)
 
 def clip_obj(obj, bbox):
     bbox = decimalize(bbox)

tests/test_basics.py

@@ -1,5 +1,6 @@
 #!/usr/bin/env python
 import unittest
+import pytest
 import pandas as pd
 import pdfplumber
 import sys, os
@@ -72,6 +73,33 @@ class Test(unittest.TestCase):
         assert id(filtered.chars) == id(filtered._objects["char"])
         assert len(filtered.rects) == 0
 
+    def test_relative_crop(self):
+        original = self.pdf.pages[0]
+        cropped = original.crop((10, 10, 40, 40))
+        recropped = cropped.crop((10, 15, 20, 25), relative=True)
+        target_bbox = pdfplumber.utils.decimalize((20, 25, 30, 35))
+        assert recropped.bbox == target_bbox
+
+        recropped_wi = cropped.within_bbox((10, 15, 20, 25), relative=True)
+        assert recropped_wi.bbox == target_bbox
+
+    def test_invalid_crops(self):
+        original = self.pdf.pages[0]
+        with pytest.raises(ValueError):
+            original.crop((0, 0, 0, 0))
+
+        with pytest.raises(ValueError):
+            original.crop((0, 0, 10000, 10))
+
+        with pytest.raises(ValueError):
+            original.crop((-10, 0, 10, 10))
+
+        with pytest.raises(ValueError):
+            original.crop((100, 0, 0, 100))
+
+        with pytest.raises(ValueError):
+            original.crop((0, 100, 100, 0))
+
     def test_rotation(self):
         assert(self.pdf.pages[0].width == 1008)
         assert(self.pdf.pages[0].height == 612)

tests/test_utils.py

@@ -96,7 +96,7 @@ class Test(unittest.TestCase):
         ])
 
         assert text == goal
-        assert self.pdf.pages[0].crop((0, 0, 0, 0)).extract_text() == None
+        assert self.pdf.pages[0].crop((0, 0, 1, 1)).extract_text() == None
 
     def test_resize_object(self):
         obj = {