frictionlessdata\tableschema\CsvDialect::parseRow()

Complexity

Conditions	29
Paths	69

Size

Total Lines	122
Code Lines	70

Duplication

Lines	35
Ratio	28.69 %

Importance

Changes

0

<?php
    public function parseRow($line)
    {
        // RFC4180      - Each record is located on a separate line, delimited by a line break (CRLF)
        // Tabular Data - The line terminator character MUST be LF or CRLF
        $line = rtrim($line, "\r\n");

        // RFC4180      - Within the header and each record, there may be one or more fields, separated by commas.
        //                Spaces are considered part of a field and should not be ignored.
        //                The last field in the record must not be followed by a comma.
        //              - Each field may or may not be enclosed in double quotes
        //                (however some programs, such as Microsoft Excel, do not use double quotes at all).
        //                If fields are not enclosed with double quotes, then double quotes may not appear inside the fields.
        //              - Fields containing line breaks (CRLF), double quotes, and commas
        //                should be enclosed in double-quotes.
        //              - If double-quotes are used to enclose fields,
        //                then a double-quote appearing inside a field must be escaped by preceding it with another double quote.
        $enclosed = null;
        $fields = [];
        $field = -1;
        $lastCharPos = mb_strlen($line)-1;
        for ($charPos = 0; $charPos < mb_strlen($line); $charPos++) {
            $char = mb_substr($line, $charPos, 1);
            if ($enclosed === null) {
                // start of a new field
                if ($char == $this->dialect["delimiter"]) {
                    if (

This code seems to be duplicated across your project.

                        // delimiter at end of line
                        ($charPos == $lastCharPos)
                        // double delimiters
                        || ($charPos != $lastCharPos && mb_substr($line, $charPos+1, 1) == $this->dialect["delimiter"])
                    ) {
                        $field++;
                        $fields[$field] = "";
                    }
                    continue;
                } else {
                    $field++;
                    $fields[$field] = "";
                    if ($char == $this->dialect["quoteChar"]) {

This code seems to be duplicated across your project.

                        $enclosed = true;
                        continue;
                    } else {
                        $enclosed = false;
                        $fields[$field] .= $char;
                        continue;
                    }
                }
            } elseif ($enclosed) {
                // processing an enclosed field
                if ($this->dialect["doubleQuote"] !== null && $char == $this->dialect["quoteChar"]) {
                    // encountered quote in doubleQuote mode
                    if ($charPos !== 0 && mb_substr($line, $charPos-1, 1) == $this->dialect["quoteChar"]) {
                        // previous char was also a double quote
                        // the quote was added in previous iteration, nothing to do here
                        continue;
                    } elseif ($charPos != $lastCharPos && mb_substr($line, $charPos+1, 1) == $this->dialect["quoteChar"]) {
                        // next char is a also a double quote - add a quote to the field
                        $fields[$field] .= $this->dialect["quoteChar"];
                        continue;
                    }
                }
                if ($this->dialect["escapeChar"]) {
                    // handle escape chars
                    if ($char == $this->dialect["escapeChar"]) {
                        // char is the escape char, add the escaped char to the string
                        if ($charPos === $lastCharPos) {
                            throw new DataSourceException("Encountered escape char at end of line");
                        } else {
                            $fields[$field] .= mb_substr($line, $charPos+1, 1);
                        }
                        continue;
                    } elseif ($charPos != 0 && mb_substr($line, $charPos-1, 1) == $this->dialect["escapeChar"]) {
                        // previous char was the escape string
                        // added the char in previous iteration, nothing to do here
                        continue;
                    }
                }
                if ($char == $this->dialect["quoteChar"]) {

This code seems to be duplicated across your project.

                    // encountered a quote signifying the end of the enclosed field
                    $enclosed = null;
                    continue;
                } else {
                    // character in enclosed field
                    $fields[$field] .= $char;
                    continue;
                }
            } else {
                // processing a non-enclosed field
                if ($char == $this->dialect["quoteChar"]) {
                    // non enclosed field - cannot have a quotes
                    throw new \Exception("Invalid csv file - if field is not enclosed with double quotes - then double quotes may not appear inside the field");
                } elseif ($char == $this->dialect["delimiter"]) {
                    // end of non-enclosed field + start of new field
                    if (

This code seems to be duplicated across your project.

                        // delimiter at end of line
                        ($charPos == $lastCharPos)
                        // double delimiters
                        || ($charPos != $lastCharPos && mb_substr($line, $charPos+1, 1) == $this->dialect["delimiter"])
                    ) {
                        $field++;
                        $fields[$field] = "";
                    }
                    $enclosed = null;
                    continue;
                } else {
                    // character in non-enclosed field
                    $fields[$field] .= $char;
                    continue;
                }
            }
        }
        if (count($fields) > 1 && mb_strlen($fields[count($fields)-1]) == 0) {
            throw new \Exception("Invalid csv file - line must not end with a comma");
        }
        if ($this->dialect["skipInitialSpace"]) {
            return array_map(function($field) {
                return ltrim($field);
            }, $fields);
        } else {
            return $fields;
        }
    }
}