Merge pull request #59 from Esukhia/fix-preview

fix(preview):
Esukhia · Dec 23, 2021 · 624f9e6 · 624f9e6
2 parents 6bba949 + 455116f
commit 624f9e6
Show file tree

Hide file tree

Showing 3 changed files with 35 additions and 33 deletions.
diff --git a/pedurma/reconstruction.py b/pedurma/reconstruction.py
@@ -20,9 +20,8 @@
 from docx import Document
 
 from pedurma.exceptions import PageNumMissing
-from pedurma.pecha import NotesPage
 from pedurma.preprocess import preprocess_google_notes, preprocess_namsel_notes
-from pedurma.preview_note_layer import update_hybird_pecha_note_layer
+from pedurma.text_report import get_text_report
 from pedurma.texts import (
     get_body_text_from_last_page,
     get_page_ann,
@@ -1036,7 +1035,7 @@ def pecha_path_2_id(pecha_path):
     return pecha_path_obj.stem
 
 
-def get_preview_text(text_id, pecha_paths=None):
+def get_reconstructed_text(text_id, pecha_paths=None):
     if pecha_paths is None:
         pecha_paths = get_pecha_paths(text_id)
     pedurmatext = get_pedurma_text_obj(text_id, pecha_paths)
@@ -1063,9 +1062,6 @@ def get_preview_text(text_id, pecha_paths=None):
             cur_vol_preview = get_vol_preview(
                 dg_body, namsel_body, dg_note_text, namsel_note_text, vol_num
             )
-            update_hybird_pecha_note_layer(
-                cur_vol_preview, pecha_paths["google"], int(vol_num)
-            )
             preview_text[f"v{int(vol_num):03}"] = cur_vol_preview
             dg_body = ""
             namsel_body = ""
@@ -1101,16 +1097,34 @@ def create_docx(text_id, chunks, path):
     return output_path
 
 
-def get_docx_text(text_id, pecha_paths=None, output_path=None):
+def get_docx_text(text_id, preview_text, output_path=None):
     if not output_path:
         (Path.home() / ".collation_docx").mkdir(parents=True, exist_ok=True)
         output_path = Path.home() / ".collation_docx"
     collation_text = ""
-    preview_text, google_pecha_id = get_preview_text(text_id, pecha_paths)
     for vol_id, text in preview_text.items():
         collation_text += f"{text}\n\n"
     collation_text = collation_text.replace("\n", "")
-    collation_text = re.sub(r"(༺.+?༻)", r"\n\g<1>\n", collation_text)
+    collation_text = re.sub(r"(\d+-\d+)", r"\n\g<1>\n", collation_text)
     chunks = split_text(collation_text)
     docx_path = create_docx(text_id, chunks, output_path)
     return docx_path
+
+
+def get_preview_text(text_id, docx_output_path, pecha_paths=None):
+    preview_text_info = {
+        "preview_text": None,
+        "google_pecha_id": None,
+        "docx_output_path": None,
+        "text_report": None,
+    }
+    preview_text, google_pecha_id = get_reconstructed_text(text_id, pecha_paths)
+    preview_text_info["preview_text"] = preview_text
+    preview_text_info["google_pecha_id"] = google_pecha_id
+    preview_text_info["docx_output_path"] = get_docx_text(
+        text_id, preview_text, docx_output_path
+    )
+    preview_text_info["text_report"] = get_text_report(
+        text_id, pecha_paths, preview_text
+    )
+    return preview_text_info
diff --git a/pedurma/text_report.py b/pedurma/text_report.py
@@ -4,6 +4,8 @@
 
 from openpecha.utils import load_yaml
 
+from pedurma.texts import get_pecha_paths
+
 
 def get_metadata(pecha_path):
     pecha_id = Path(pecha_path).stem
@@ -39,6 +41,8 @@ def get_text_report(text_id, pecha_paths, preview_text):
         "total_number_of_footnotes": None,
         "download_date": None,
     }
+    if pecha_paths is None:
+        pecha_paths = get_pecha_paths(text_id)
     text_report["title"] = get_text_title(pecha_paths["google"])
     number_of_pages = 0
     number_of_footnotes = 0

diff --git a/tests/preview/test_get_preview.py b/tests/preview/test_get_preview.py
@@ -5,7 +5,11 @@
 
 from pedurma.exceptions import PageNumMissing
 from pedurma.pecha import NotesPage, Page
-from pedurma.reconstruction import get_docx_text, get_preview_page, get_preview_text
+from pedurma.reconstruction import (
+    get_docx_text,
+    get_preview_page,
+    get_reconstructed_text,
+)
 from pedurma.utils import from_yaml
 
 
@@ -14,16 +18,7 @@ def get_dummy_preview():
     namsel_pecha_path = str(Path(__file__).parent / "data" / "P973")
     text_id = "D1119"
     pecha_paths = {"namsel": namsel_pecha_path, "google": dg_pecha_path}
-    preview_text = get_preview_text(text_id, pecha_paths)
-    (
-        Path(__file__).parent
-        / "data"
-        / "P972"
-        / "P972.opf"
-        / "layers"
-        / "v001"
-        / "PedurmaNote.yml"
-    ).unlink()
+    preview_text = get_reconstructed_text(text_id, pecha_paths)
     return preview_text
 
 
@@ -151,19 +146,8 @@ def test_get_preview_text():
 def test_get_docx_text():
     text_id = "D1119"
     output_path = Path.home()
-    dg_pecha_path = str(Path(__file__).parent / "data" / "P972")
-    namsel_pecha_path = str(Path(__file__).parent / "data" / "P973")
-    pecha_paths = {"namsel": namsel_pecha_path, "google": dg_pecha_path}
-    docx_path = get_docx_text(text_id, pecha_paths, output_path)
+    preview_text, google_pecha_id = get_dummy_preview()
+    docx_path = get_docx_text(text_id, preview_text, output_path)
     expected_path = Path.home() / "D1119.docx"
     assert docx_path == expected_path
     expected_path.unlink()
-    (
-        Path(__file__).parent
-        / "data"
-        / "P972"
-        / "P972.opf"
-        / "layers"
-        / "v001"
-        / "PedurmaNote.yml"
-    ).unlink()