Created:
| Last Modified:
Continuing with my earlier idea by separating text file into sections and then parsing those sections (this recording partially covers this topic ).
Names Default To Here(1);
// Test sections seem to always start with a line starting with "SetupTitle"
// and end to same UNLESS it is last section when it ends with
// line of ",,,,,,,,,,,,,,,,,,,,,,,"
TEST_SECTION_START = "SetupTitle, ";
EMPTY_LINE = ",,,,,,,,,,,,,,,,,,,,,,,";
// Section patterns for regex
PROJECT_PATTERN = "^(.+)_(\d+\.\d*)(W\d{1,2})_(T\d+)_(.+): (\d+ \d+)\,+?";
SUBSITE_PATTERN = "<Subsite>(\d+)</Subsite>";
DATASTART_PATTERN = "^DataName";
find_test_section_lines = function({lines}, {Default Local},
start_idx = 0;
end_idx = 0;
TEST_SECTION_START = TEST_SECTION_START; // JMP "feature", 00075244
TEST_SECTION_END = TEST_SECTION_END; // JMP "feature", 00075244
For Each({line, idx}, lines,
If(Starts With(line, TEST_SECTION_START),
If(start_idx == 0,
start_idx = idx;
,
end_idx = idx;
break();
);
);
);
If(start_idx != 0 & end_idx == 0,
end_idx = N Items(lines);
);
return(Eval List({start_idx, end_idx}));
);
parse_test_section = function({lines}, {Default Local},
data_start = 0;
PROJECT_PATTERN = PROJECT_PATTERN; //JMP "feature", 00075244
SUBSITE_PATTERN = SUBSITE_PATTERN; //JMP "feature", 00075244
DATASTART_PATTERN = DATASTART_PATTERN; //JMP "feature", 00075244
For Each({line, idx}, lines,
If(!IsMissing(Regex(line, PROJECT_PATTERN)),
matches = Regex Match(line, PROJECT_PATTERN);
projname = matches[2];
lotid = matches[3];
waferid = matches[4];
time = matches[5];
notes = matches[6];
reticles = Words(Trim Whitespace(matches[7]), " ");
, !IsMissing(Regex(line, SUBSITE_PATTERN)),
subsite = Regex(line, SUBSITE_PATTERN, "\1");
, !IsMissing(Regex(line, DATASTART_PATTERN)),
data_start = idx;
break();
);
);
data_str = Concat Items(lines[data_start::N Items(lines)], "\!N");
dt = Open(Char To Blob(data_str), "text", invisible);
For Each({colname}, Reverse(dt << Get Column Names("String")), // drop empty columns
If(Col Number(Column(dt, colname)) == 0,
dt << Delete Column(colname);
,
break(); // break on first "ok" column
);
);
// define order and names here
dt << New Column("project", Character, Nominal, Set Each Value(projname));
dt << New Column("lot", Character, Nominal, Set Each Value(lotid));
dt << New Column("waferid", Character, Nominal, Set Each Value(waferid));
dt << New Column("time", Character, Nominal, Set Each Value(time));
dt << New Column("notes", Character, Nominal, Set Each Value(notes));
dt << New Column("x", Character, Nominal, Set Each Value(reticles[1]));
dt << New Column("y", Character, Nominal, Set Each Value(reticles[2]));
dt << New Column("subsite", Character, Nominal, Set Each Value(subsite));
dt << Move Selected Columns({:project, :lot, :waferid, :time, :notes, :x, :y, :subsite}, To First);
dt << Delete Columns("DataName");
return(dt);
);
// Start parsing
filepath = "$DOWNLOADS/Raw data examples_3DP.csv";
txt = Load Text File(filepath);
lines = Words(txt, "\!N");
lines = Filter Each({line}, lines, line != EMPTY_LINE); // drop empty lines
{start, end} = find_test_section_lines(lines);
dt_result = Empty();
While(All(start, end),
cur_testset = Remove From(lines, start, end - 1);
dt = parse_test_section(cur_testset);
If(Is Empty(dt_result),
dt_result = dt;
,
dt_result << Concatenate(
dt,
"Append to first table"
);
Close(dt, no save);
);
{start, end} = find_test_section_lines(lines);
);
dt_result << Show Window(1);
Created:
| Last Modified:
Depending on your application, you might be able to make the parser more robust by looking for repeating patterns instead of relying on regex patterns matching specific lines. For example it looks like your project name for example is between MetaData lines
Depending on the assumptions you can make, you could extract it based on those MetaData and "empty" lines instead of relying on "line starts with Proj" or "line matches this regex pattern".