kodexa 7.0.11920845564__py3-none-any.whl → 7.0.12260797471__py3-none-any.whl

kodexa/model/objects.py

@@ -5468,7 +5468,6 @@ class DataForm(ExtensionPackProvided):
 
     """
     entrypoints: Optional[List[str]] = None
-    entrypoint: Optional[str] = None
     cards: Optional[List[Card]] = None
     filters: Optional[str] = None
 
@@ -5488,6 +5487,7 @@ class ProjectDataForm(BaseModel):
     description: Optional[str] = None
 
     cards: Optional[List[Card]] = None
+    entrypoints: Optional[List[str]] = None
 
     ref: Optional[str] = None
 

kodexa/model/utils.py

@@ -0,0 +1,92 @@
+import logging
+
+from kodexa import ContentNode
+
+logger = logging.getLogger(__name__)
+
+def get_pretty_text_from_lines(lines: list[ContentNode], scale, include_line_uuid=False) -> str:
+    pretty_text = ""
+    for line_index, line in enumerate(lines):
+        line_content = f"('{line.uuid}')" if include_line_uuid else ""
+        current_x = 0
+        for word in line.select('//word'):
+            x = int(word.get_bbox()[0] * scale)
+            spaces_needed = max(1, x - current_x)  # Ensure at least one space
+            line_content += " " * spaces_needed
+            line_content += f"{word.get_all_content()}"
+            current_x = x + len(word.get_all_content())
+
+        pretty_text += line_content + "\n"
+
+    return pretty_text
+
+
+def get_max_width(lines: list[ContentNode], max_width=None) -> int:
+    if max_width is None:
+        # Find the line with the most words
+        max_words_line = max(lines, key=lambda line: sum(len(word.get_all_content()) for word in line.select('//word')))
+
+        # Calculate max_width based on the length of all words plus spaces
+        max_width = sum(len(word.get_all_content()) for word in max_words_line.select('//word')) + (len(max_words_line.select('//word'))*4) - 1
+
+    if max_width < 250:
+        max_width = 250
+
+    return max_width
+
+
+def get_scale_from_words(words: list[ContentNode], max_width) -> float:
+    # Get the bboxes
+    bboxes = [word.get_bbox() for word in words]
+
+    # Find the overall bounding box
+    min_x = min(bbox[0] for bbox in bboxes)
+    max_x = max(bbox[2] for bbox in bboxes)
+    min_y = min(bbox[1] for bbox in bboxes)
+    max_y = max(bbox[3] for bbox in bboxes)
+
+    # Invert y-axis
+    max_y, min_y = min_y, max_y
+
+    # Calculate scale factor to fit within max_width
+    scale = max_width / (max_x - min_x)
+
+    return scale
+
+
+def get_pretty_page(page: ContentNode, max_width=None, include_line_uuid=False) -> str:
+    """
+    Get a pretty representation of the page
+
+    :param page: The page to get the pretty representation for
+    :param max_width: The maximum width of the page
+    :param include_line_uuid: Include the line UUID in the pretty representation
+
+    :return: A pretty representation of the page
+    """
+
+    logger.info(f"Getting pretty page {page.index}")
+
+    pretty_text = ""
+    content_areas = page.select('//content-area')
+
+    lines = page.select('//line')
+
+    max_width = get_max_width(lines, max_width)
+    logger.info(f"Max width: {max_width}")
+
+    words = page.select('//word')
+    if len(words) == 0:
+        return page.get_all_content()
+
+    scale = get_scale_from_words(words, max_width)
+    for area_index, area in enumerate(content_areas):
+
+        if area_index > 0:
+            pretty_text += "\n\n"  # Add extra newline between content areas
+
+        pretty_text += get_pretty_text_from_lines(area.select('//line'), scale, include_line_uuid)
+
+    logger.debug(f"Pretty Page: {page.index}: \n{pretty_text}")
+
+    return pretty_text

{kodexa-7.0.11920845564.dist-info → kodexa-7.0.12260797471.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: kodexa
-Version: 7.0.11920845564
+Version: 7.0.12260797471
 Summary: Python SDK for the Kodexa Platform
 Author: Austin Redenbaugh
 Author-email: austin@kodexa.com

{kodexa-7.0.11920845564.dist-info → kodexa-7.0.12260797471.dist-info}/RECORD

@@ -12,8 +12,9 @@ kodexa/model/entities/check_response.py,sha256=eqBHxO6G2OAziL3p9bHGI-oiPkAG82H6C
 kodexa/model/entities/product.py,sha256=ZDpHuBE_9FJ-klnkyBvTfPwYOqBkM1wraZMtHqNA8FQ,3526
 kodexa/model/entities/product_subscription.py,sha256=UcmWR-qgLfdV7VCtJNwzgkanoS8nBSL6ngVuxQUK1M8,3810
 kodexa/model/model.py,sha256=wY5HnpsAnKlH_aDEHWNf-ZrhdrBg-DtqGFszjkdZtPU,118340
-kodexa/model/objects.py,sha256=CE76KwQwIT6FdWJuac8aIumX_Ok6-9oq1JXz0K_gdwo,185117
+kodexa/model/objects.py,sha256=4Oyjs6omlHfwziAK1m2tFk4jSnzN7lFdXACog07ed1c,185124
 kodexa/model/persistence.py,sha256=PTh9jmqYCDuWfiuCssLttFaYWiMA_fCiwjgsYDW4AhE,68281
+kodexa/model/utils.py,sha256=6R-3rFiW9irBwj0Mq5yhp7EDXkNUFaeFhr3bWmnlW4g,2961
 kodexa/pipeline/__init__.py,sha256=sA7f5D6qkdMrpp2xTIeefnrUBI6xxEEWostvxfX_1Cs,236
 kodexa/pipeline/pipeline.py,sha256=ZYpJAWcwV4YRK589DUhU0vXGQlkNSj4J2TsGbYqTLjo,25221
 kodexa/platform/__init__.py,sha256=1O3oiWMg292NPL_NacKDnK1T3_R6cMorrPRue_9e-O4,216
@@ -42,7 +43,7 @@ kodexa/testing/test_utils.py,sha256=DrLCkHxdb6AbZ-X3WmTMbQmnVIm55VEBL8MjtUK9POs,
 kodexa/training/__init__.py,sha256=xs2L62YpRkIRfslQwtQZ5Yxjhm7sLzX2TrVX6EuBnZQ,52
 kodexa/training/train_utils.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 kodexa/utils/__init__.py,sha256=Pnim1o9_db5YEnNvDTxpM7HG-qTlL6n8JwFwOafU9wo,5928
-kodexa-7.0.11920845564.dist-info/LICENSE,sha256=WNHhf_5RCaeuKWyq_K39vmp9F28LxKsB4SpomwSZ2L0,11357
-kodexa-7.0.11920845564.dist-info/METADATA,sha256=rL71hJphMwIizznP28gRoyhyo9-tviViV3gaTl_zU4A,3527
-kodexa-7.0.11920845564.dist-info/WHEEL,sha256=Zb28QaM1gQi8f4VCBhsUklF61CTlNYfs9YAZn-TOGFk,88
-kodexa-7.0.11920845564.dist-info/RECORD,,
+kodexa-7.0.12260797471.dist-info/LICENSE,sha256=WNHhf_5RCaeuKWyq_K39vmp9F28LxKsB4SpomwSZ2L0,11357
+kodexa-7.0.12260797471.dist-info/METADATA,sha256=05A83UZeGYAMX48VXMOh-geCtXObL4lfIEx6QxCIE5s,3527
+kodexa-7.0.12260797471.dist-info/WHEEL,sha256=Zb28QaM1gQi8f4VCBhsUklF61CTlNYfs9YAZn-TOGFk,88
+kodexa-7.0.12260797471.dist-info/RECORD,,