Update page_files/categorized/Backend/mapper5.py

page_files/categorized/Backend/mapper5.py

@@ -651,8 +651,8 @@ def run_full_pipeline(
     """Run Code 1 (2.py) extraction, Code 2 (image2.py) plots, then map.
     `source_table` ∈ {consensus, verified, consensus_verified, gemini, gpt, claude}."""
     import importlib
-    run_pipeline = importlib.import_module("2").run_pipeline  # Code 1 = 2.py
-    from image2 import extract_and_verify_plots               # Code 2 = image2.py
+    run_pipeline = importlib.import_module("Pdf_DataExtraction").run_pipeline  # Code 1 = 2.py
+    from Pdf_ImageExtraction import extract_and_verify_plots               # Code 2 = image2.py
 
     (df_consensus, df_verified, df_consensus_verified,
      df_gemini, df_gpt, df_claude,
@@ -1117,7 +1117,7 @@ def _extract(pdf_bytes: bytes, doi_override: str = "",
     six property tables + plot_results + coverage + meta + errors."""
     import importlib
     run_pipeline = importlib.import_module("2").run_pipeline
-    from image2 import extract_and_verify_plots
+    from Pdf_ImageExtraction import extract_and_verify_plots
     (dfc, dfv, dfcv, dfg, dfp, dfcl, _chunks, errors, meta) = run_pipeline(
         pdf_bytes, doi_override=doi_override)
     plot_results, coverage = extract_and_verify_plots(
@@ -1135,7 +1135,7 @@ def _extract(pdf_bytes: bytes, doi_override: str = "",
 def get_or_extract(pdf_bytes: bytes, doi_override: str = "", verify_engines=None,
                    use_disk_cache: bool = True, force: bool = False):
     """Extraction cached by the PDF's CONTENT HASH — never by source_table.
-    On a cache hit, 2.py and image2.py are NOT re-run, so switching tables /
+    On a cache hit, Pdf_DataExtraction.py and Pdf_ImageExtraction.py are NOT re-run, so switching tables /
     pruning / re-mapping is free. Returns (pdf_hash, bundle)."""
     import pickle
     h = _pdf_hash(pdf_bytes)
@@ -1194,7 +1194,7 @@ def _run_streamlit() -> None:
 
     st.set_page_config(page_title="mapper — Plot ⇄ Property", page_icon="🔗", layout="wide")
     st.title("🔗 mapper — Plot ⇄ Property mapping + database")
-    st.caption("Runs 2.py + image2.py once (cached), auto-drops non-plots, lets you "
+    st.caption("Runs Pdf_DataExtraction.py + Pdf_ImageExtraction.py once (cached), auto-drops non-plots, lets you "
                "prune what's left, then attaches plots to properties on Map.")
 
     ss = st.session_state
@@ -1250,7 +1250,7 @@ def _run_streamlit() -> None:
         use_claude = st.checkbox("Also verify crops with Claude", value=False)
         doi_manual = st.text_input("DOI override (optional)", placeholder="10.xxxx/...")
         use_disk_cache = st.checkbox("Use on-disk extraction cache", value=True,
-                                     help="Skip 2.py + image2.py entirely when this exact "
+                                     help="Skip Pdf_DataExtraction.py + Pdf_ImageExtraction.py entirely when this exact "
                                           "PDF was extracted before.")
         st.divider()
         st.subheader("Auto figure filter")
@@ -1292,12 +1292,12 @@ def _run_streamlit() -> None:
                                 use_container_width=True)
     else:
         ec1.success("✓ This paper is loaded — switch tables / prune / map freely; "
-                    "2.py and image2.py will NOT re-run.")
+                    "Pdf_DataExtraction.py and Pdf_ImageExtraction.py will NOT re-run.")
     force = ec2.button("↻ Force re-extract", use_container_width=True)
 
     if do_extract or force:
         engines = ["gemini"] + (["gpt"] if use_gpt else []) + (["claude"] if use_claude else [])
-        with st.spinner("Running 2.py extraction/consensus + image2.py plot detection…"):
+        with st.spinner("Running Pdf_DataExtraction.py extraction/consensus + Pdf_ImageExtraction.py plot detection…"):
             _h, bundle = get_or_extract(pdf_bytes, doi_override=doi_manual,
                                         verify_engines=engines,
                                         use_disk_cache=use_disk_cache, force=force)
@@ -1314,11 +1314,11 @@ def _run_streamlit() -> None:
     bundle = ss["bundle"]
     stem = ss["stem"]
     if bundle.get("_cache") == "disk":
-        st.caption("↩ Loaded from on-disk cache — 2.py and image2.py were not re-run.")
+        st.caption("↩ Loaded from on-disk cache — Pdf_DataExtraction.py and Pdf_ImageExtraction.py were not re-run.")
 
     # ---- three top-level views ---------------------------------------------
     view_props, view_plots, work = st.tabs(
-        ["📄 Extraction (2.py)", "🖼️ Plots (image2.py)", "🔗 Map & curate"])
+        ["📄 Extraction (2.py)", "🖼️ Plots (Pdf_ImageExtraction.py)", "🔗 Map & curate"])
 
     with view_props:
         if bundle.get("api_errors"):