fix: set page number using 1-based indexing (#22)

Signed-off-by: Panos Vagenas <[email protected]>
DS4SD · Jul 31, 2024 · d2d9543 · d2d9543
1 parent e102827
commit d2d9543
Show file tree

Hide file tree

Showing 4 changed files with 11 additions and 11 deletions.
diff --git a/README.md b/README.md
@@ -56,7 +56,7 @@ print(doc.export_to_markdown())  # output: "## DocLayNet: A Large Human-Annotate
 
 ### Convert a batch of documents
 
-For an example of converting multiple documents, see [convert.py](https://github.com/DS4SD/docling/blob/main/examples/convert.py).
+For an example of batch-converting documents, see [convert.py](https://github.com/DS4SD/docling/blob/main/examples/convert.py).
 
 From a local repo clone, you can run it with:
 

diff --git a/docling/datamodel/document.py b/docling/datamodel/document.py
@@ -125,7 +125,7 @@ def to_ds_document(self) -> DsDocument:
         desc = DsDocumentDescription(logs=[])
 
         page_hashes = [
-            PageReference(hash=p.page_hash, page=p.page_no, model="default")
+            PageReference(hash=p.page_hash, page=p.page_no + 1, model="default")
             for p in self.pages
         ]
 
@@ -159,7 +159,7 @@ def to_ds_document(self) -> DsDocument:
                         prov=[
                             Prov(
                                 bbox=target_bbox,
-                                page=element.page_no,
+                                page=element.page_no + 1,
                                 span=[0, len(element.text)],
                             )
                         ],
@@ -242,7 +242,7 @@ def make_spans(cell):
                         prov=[
                             Prov(
                                 bbox=target_bbox,
-                                page=element.page_no,
+                                page=element.page_no + 1,
                                 span=[0, 0],
                             )
                         ],
@@ -264,7 +264,7 @@ def make_spans(cell):
                         prov=[
                             Prov(
                                 bbox=target_bbox,
-                                page=element.page_no,
+                                page=element.page_no + 1,
                                 span=[0, 0],
                             )
                         ],
@@ -274,7 +274,7 @@ def make_spans(cell):
                 )
 
         page_dimensions = [
-            PageDimensions(page=p.page_no, height=p.size.height, width=p.size.width)
+            PageDimensions(page=p.page_no + 1, height=p.size.height, width=p.size.width)
             for p in self.pages
         ]
 

diff --git a/poetry.lock b/poetry.lock
diff --git a/pyproject.toml b/pyproject.toml
@@ -23,7 +23,7 @@ packages = [{include = "docling"}]
 [tool.poetry.dependencies]
 python = "^3.10"
 pydantic = "^2.0.0"
-docling-core = "^1.1.0"
+docling-core = "^1.1.2"
 docling-ibm-models = "^1.1.0"
 deepsearch-glm = ">=0.19.0,<1"
 filetype = "^1.2.0"