Merge branch 'master' into fix-split-bug

HISTORY.md

@@ -7,6 +7,7 @@ master
 **Bugfixes**
 
 * [#293](https://github.com/socialcopsdev/camelot/issues/293) Split text ignores all text to the right of last cut. [#294](https://github.com/socialcopsdev/camelot/pull/294) by Vinayak Mehta.
+* [#277](https://github.com/socialcopsdev/camelot/issues/277) Sort TableList by order of tables in PDF. [#283](https://github.com/socialcopsdev/camelot/pull/283) by [Sym Roe](https://github.com/symroe).
 
 0.7.2 (2019-01-10)
 ------------------

camelot/core.py

@@ -329,6 +329,13 @@ class Table(object):
     def __repr__(self):
         return '<{} shape={}>'.format(self.__class__.__name__, self.shape)
 
+    def __lt__(self, other):
+        if self.page == other.page:
+            if self.order < other.order:
+                return True
+        if self.page < other.page:
+            return True
+
     @property
     def data(self):
         """Returns two-dimensional list of strings in table.

camelot/handlers.py

@@ -161,4 +161,4 @@ class PDFHandler(object):
                 t = parser.extract_tables(p, suppress_stdout=suppress_stdout,
                                           layout_kwargs=layout_kwargs)
                 tables.extend(t)
-        return TableList(tables)
+        return TableList(sorted(tables))

tests/test_common.py

@@ -5,6 +5,7 @@ import os
 import pandas as pd
 
 import camelot
+from camelot.core import Table, TableList
 
 from .data import *
 
@@ -247,3 +248,28 @@ def test_arabic():
     filename = os.path.join(testdir, "tabula/arabic.pdf")
     tables = camelot.read_pdf(filename)
     assert df.equals(tables[0].df)
+
+
+def test_table_order():
+    def _make_table(page, order):
+        t = Table([], [])
+        t.page = page
+        t.order = order
+        return t
+
+    table_list = TableList(
+        [_make_table(2, 1), _make_table(1, 1), _make_table(3, 4), _make_table(1, 2)]
+    )
+
+    assert [(t.page, t.order) for t in sorted(table_list)] == [
+        (1, 1),
+        (1, 2),
+        (2, 1),
+        (3, 4),
+    ]
+    assert [(t.page, t.order) for t in sorted(table_list, reverse=True)] == [
+        (3, 4),
+        (2, 1),
+        (1, 2),
+        (1, 1),
+    ]