Tweak #467 code slightly, update CHANGELOG/thanks

h/t @bobluda + @samkit-jain
jsvine · Jul 15, 2021 · 9019854 · 9019854
1 parent 3ce87eb
commit 9019854
Show file tree

Hide file tree

Showing 3 changed files with 20 additions and 18 deletions.
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -3,6 +3,9 @@
 All notable changes to this project will be documented in this file. The format is based on [Keep a Changelog](http://keepachangelog.com/).
 
 ## [0.5.29] - [unreleased]
+## Changed
+- Change behavior of horizontal `text_strategy`, so that it uses the top and bottom of *every* word, not just the top of every word and the bottom of the last. ([#467](https://github.com/jsvine/pdfplumber/pull/467) + [#466](https://github.com/jsvine/pdfplumber/issues/466) + [#265](https://github.com/jsvine/pdfplumber/issues/265)) [h/t @bobluda + @samkit-jain]
+
 ### Development Changes
 - Add `CONTRIBUTING.md` ([#428](https://github.com/jsvine/pdfplumber/pull/428))
 

diff --git a/README.md b/README.md
@@ -431,6 +431,7 @@ Many thanks to the following users who've contributed ideas, features, and fixes
 - [xv44586](https://github.com/xv44586)
 - [Alexander Regueiro](https://github.com/alexreg)
 - [Daniel Peña](https://github.com/trifling)
+- [bobluda](https://github.com/bobluda)
 
 ## Contributing
 

diff --git a/pdfplumber/table.py b/pdfplumber/table.py
@@ -85,32 +85,30 @@ def words_to_edges_h(words, word_threshold=DEFAULT_MIN_WORDS_HORIZONTAL):
     min_x0 = min(map(itemgetter("x0"), rects))
     max_x1 = max(map(itemgetter("x1"), rects))
 
-    edges = [
-        {
-            "x0": min_x0,
-            "x1": max_x1,
-            "top": r["top"],
-            "bottom": r["top"],
-            "width": max_x1 - min_x0,
-            "orientation": "h",
-        }
-        for r in rects
-    ]
-
-    # For each detected row, we also add the 'bottom' line.
-    # This will generate extra edges, (some will be redundant with the next row
-    # 'top' line), but this catches the last row of every table.
+    edges = []
     for r in rects:
-        edges.append(
+        edges += [
+            # Top of text
+            {
+                "x0": min_x0,
+                "x1": max_x1,
+                "top": r["top"],
+                "bottom": r["top"],
+                "width": max_x1 - min_x0,
+                "orientation": "h",
+            },
+            # For each detected row, we also add the 'bottom' line.  This will
+            # generate extra edges, (some will be redundant with the next row
+            # 'top' line), but this catches the last row of every table.
             {
                 "x0": min_x0,
                 "x1": max_x1,
                 "top": r["bottom"],
                 "bottom": r["bottom"],
                 "width": max_x1 - min_x0,
                 "orientation": "h",
-            }
-        )
+            },
+        ]
 
     return edges