def format_diff(a: Table, b: Table, index: List[str] = []) -> str:
flags = daff.CompareFlags()
for name in index:
flags.addPrimaryKey(name)
diff = daff.Coopy.diff(a, b, flags=flags)
output = daff.TerminalDiffRender().render(diff)
return output
def diff_tsv(self, other, filename, exclude_fields):
# We will store our variables in these lists
with open(os.path.join(self.path, filename)) as self_file:
self_dataframe = pandas.read_csv(self_file, delimiter='\t')
self_dataframe_filtered = self_dataframe.drop(filter(
lambda field: field in self_dataframe.columns, exclude_fields),
axis=1)
self_list = [self_dataframe_filtered.columns.tolist()
] + self_dataframe_filtered.values.tolist()
self_data = daff.PythonTableView(self_list)
with open(os.path.join(other.path, filename)) as other_file:
other_dataframe = pandas.read_csv(other_file, delimiter='\t')
other_dataframe_filtered = other_dataframe.drop(filter(
lambda field: field in other_dataframe.columns,
exclude_fields),
axis=1)
other_list = [other_dataframe_filtered.columns.tolist()
] + other_dataframe_filtered.values.tolist()
other_data = daff.PythonTableView(other_list)
alignment = daff.Coopy.compareTables(self_data, other_data).align()
result = daff.PythonTableView([])
diff = daff.TableDiff(alignment, daff.CompareFlags())
diff.hilite(result)
if diff.hasDifference():
return daff.TerminalDiffRender().render(result)
else:
return None
def get_diff(self, filename1, filename2):
#print("get_diff", filename1, filename2)
ext = filename1.split(".")[-1].lower()
if ext not in ['csv', 'tsv', 'xls']:
return None
csvs = {}
for f in [filename1, filename2]:
# print("Loading file", f)
table_set = self.read_file(f)
if table_set is None:
raise Exception("Invalid table set")
row_set = table_set.tables[0]
#print("Guessing headers")
offset, headers = headers_guess(row_set.sample)
row_set.register_processor(headers_processor(headers))
row_set.register_processor(offset_processor(offset + 1))
# Output of rowset is a structure
csvs[f] = [headers]
for row in row_set:
csvs[f].append([r.value for r in row])
#print(csvs[f][:3])
# Loaded csv1 and csv2
table1 = daff.PythonTableView(csvs[filename1])
table2 = daff.PythonTableView(csvs[filename2])
alignment = daff.Coopy.compareTables(table1, table2).align()
# print("Achieved alignment")
data_diff = []
table_diff = daff.PythonTableView(data_diff)
flags = daff.CompareFlags()
highlighter = daff.TableDiff(alignment, flags)
highlighter.hilite(table_diff)
# Parse the differences
#print("Parsing diff")
diff = self.parse_diff(table_diff)
#print("Computed diff", diff)
return diff
def process_ids(prev_file, curr_file, prev_id_file, id_file):
io = daff.TableIO()
dapp = daff.Coopy(io)
if not os.path.exists(prev_file):
prev_file = curr_file
v1 = dapp.loadTable(prev_file, 'local')
v2 = dapp.loadTable(curr_file, 'remote')
flags = daff.CompareFlags()
flags.allow_nested_cells = True
alignment = daff.compareTables3(None, v1, v2, flags).align()
daff.TableDiff(alignment, flags).hiliteSingle(daff.SimpleTable(0, 0))
if os.path.exists(prev_id_file):
in_refs = json.load(open(prev_id_file))
else:
in_refs = {}
out_refs = {}
for part in alignment.comp.child_order:
comp = alignment.comp.children.get(part)
nalignment = comp.alignment
order = nalignment.toOrder().getList()
v1 = comp.a
v2 = comp.b
ref = in_refs.get(part, {})
if part not in out_refs:
out_ref = out_refs[part] = {}
mints = 0
copies = 0
drops = 0
for o in order:
if o.r == 0:
continue
if o.r >= 0 and o.l >= 0:
src = ref.get(str(o.l))
if src is None:
out_ref[o.r] = str(uuid.uuid4())
mints += 1
else:
out_ref[o.r] = ref[str(o.l)]
copies += 1
if o.r < 0 and o.l >= 0:
drops += 1
if o.r >= 0 and o.l < 0:
out_ref[o.r] = str(uuid.uuid4())
mints += 1
json.dump(out_refs, open(id_file, 'w'), indent=2)
return out_refs
['Ireland','Dublin'], ['France','Paris'], ['Spain','Barcelona'] ] data2 = [ ['Country','Code','Capital'], ['Ireland','ie','Dublin'], ['France','fr','Paris'], ['Spain','es','Madrid'], ['Germany','de','Berlin'] ] table1 = daff.PythonTableView(data1) table2 = daff.PythonTableView(data2) alignment = daff.Coopy.compareTables(table1,table2).align() data_diff = [] table_diff = PythonTableView(data_diff) flags = daff.CompareFlags() highlighter = daff.TableDiff(alignment,flags) highlighter.hilite(table_diff) diff2html = daff.DiffRender() diff2html.usePrettyArrows(False) diff2html.render(table_diff) table_diff_html = diff2html.html() print(table_diff_html)