List <Dictionary <string, int> > GetALUSets(ExcelQuery query, bool compareRows, List <string> searchTerms, List <string> excludes)
{
List <Dictionary <string, int> > set = new List <Dictionary <string, int> >();
List <List <string> > list = new List <List <string> >();
string err = string.Empty;
//Get 1st sheet
string[] sheets = query.GetSheetNames();
if (sheets == null || sheets.Length > 1)
{
Debug.LogError("Sheet missing or more than one sheet! Quitting");
return(null);
}
//use first sheet in our query, whatever it is named
query.GetNewSheet(sheets[0]);
//Get titles
string[] titles = query.GetTitle(0, ref err);
if (titles == null)
{
Debug.Log("No titles found! Quitting");
return(null);
}
int len = titles.Length;
int uid_col = SheetUtils.FindMatchIndexesInStringArr(titles, UID_ColumnNames.ToArray())[0];
if (uid_col < 0)
{
Debug.LogError(string.Format("couldn't find UID column"));
return(null);
}
else
{
Debug.Log(string.Format("Found uid_column at {0} which is header {1}", uid_col, query.GetHeaderColumnName(uid_col)));
}
HashSet <int> skips = new HashSet <int>(SheetUtils.FindMatchIndexesInStringArr(titles, UPC_ColumnNames.ToArray()));
//search titles for "UPC" or "Barcode"
for (int col = 0; col < len; col++)
{
foreach (string heading in searchTerms)
{
if (titles[col].Contains(heading, StringComparison.OrdinalIgnoreCase))
{
bool exclude = false;
foreach (string exclusion in excludes)
{
if (titles[col].Contains(exclusion, StringComparison.OrdinalIgnoreCase))
{
exclude = true;
}
}
if (exclude)
{
continue;
}
Dictionary <string, int> column = new Dictionary <string, int>();
set.Add(column);
List <string> sublist = new List <string>();
list.Add(sublist);
//add all values for that column to dictionary with row as value
string[] vals = query.GetColumn <string>(col, "(_._)");
for (int row = 0; row < vals.Length; row++)
{
string val = vals[row];
if (val == "(_._)")
{
continue; //skip our null sentinel
}
sublist.Add(val);
if (column.ContainsKey(val))
{
if (compareRows)
{
LogResult(string.Format("found {0} misses between row {1} and row {2}", Compare_Rows_Skip_Mismatched_UPC_If_ItemIDs_Equal(query, row + 1, column[val] + 1, titles.Length, uid_col, skips),
column[val] + 1, row + 1));
}
else
{
LogResult(string.Format("Current row:{0} Subset for column:{1} already contains val:{2} at row:{3}", row + 2, query.GetHeaderColumnName(col), val, column[val] + 2));
}
}
else
{
column.Add(val, row);
}
}
}
}
}
aluColumns.Add(list);
return(set);
}
void ColumnCheck(ExcelQuery query, string heading)
{
string err = string.Empty;
//use first sheet in our query, whatever it is named
query.GetNewSheet(query.GetSheetNames()[0]);
//Get titles
string[] titles = query.GetTitle(0, ref err);
if (titles == null)
{
Debug.Log("No titles found! Quitting");
return;
}
int len = titles.Length;
int uid_col = SheetUtils.FindMatchIndexesInStringArr(titles, UID_ColumnNames.ToArray())[0];
if (uid_col < 0)
{
Debug.LogError(string.Format("couldn't find UID column"));
return;
}
else
{
Debug.Log(string.Format("Found uid_column at {0} which is header {1}", uid_col, query.GetHeaderColumnName(uid_col)));
}
for (int col = 0; col < len; col++)
{
if (titles[col].Equals(heading, StringComparison.OrdinalIgnoreCase))
{
Dictionary <long, int> column = new Dictionary <long, int>();
//add all values for that column to dictionary with row as value
long[] vals = query.GetColumn <long>(col, -1);
for (int row = 0; row < vals.Length; row++)
{
long val = vals[row];
if (val == -1)
{
continue; //skip our null sentinel
}
if (column.ContainsKey(val))
{
string[] duplicate = query.GetRow(row + 1, "(_._)", len);
string[] original = query.GetRow(column[val] + 1, "(_._)", len);
int result = CompareRows(duplicate, original);
if (result < 3 && original[uid_col] != duplicate[uid_col])
{
LogResult(string.Format("Problem! found almost duplicate upc and row (misses:{0}) with non-identical itemids: row {1} (item:{3}) and row {2} (item:{4})", result, column[val] + 1, row + 1, original[uid_col], duplicate[uid_col]));
continue;
}
if (result > 2 && original[uid_col] == duplicate[uid_col])
{
LogResult(string.Format("Problem! found duplicate upc with non-duplicate rows (misses:{0}) but with identical itemids: row {1} (item:{3}) and row {2} (item:{4})", result, column[val] + 1, row + 1, original[uid_col], duplicate[uid_col]));
continue;
}
if (result < 3 && result > 0)
{
LogResult(string.Format("found almost duplicate upc/itemid (misses:{0}) we expect item:{1} at row:{2} will not be added because item:{3} exists at row:{4}", result, duplicate[uid_col], row + 1, original[uid_col], column[val] + 1));
continue;
}
if (result < 1)
{
LogResult(string.Format("found duplicate upc/itemid (misses:{0}) we expect item:{1} at row:{2} will not be added because item:{3} exists at row:{4}", result, duplicate[uid_col], row + 1, original[uid_col], column[val] + 1));
continue;
}
if (result > 2)
{
LogResult(string.Format("found non-duplicate items with the same UPC: {0} misses between row {1} (item:{3}) and row {2} (item:{4})", result, column[val] + 1, row + 1, original[uid_col], duplicate[uid_col]));
continue;
}
LogResult(string.Format("somehow managed to miss a case: found {0} misses between row {1} (item:{3}) and row {2} (item:{4})", result, column[val] + 1, row + 1, original[uid_col], duplicate[uid_col]));
}
else
{
column.Add(val, row);
}
}
}
}
return;
}