X-Git-Url: http://www.git.cypherpunks.ru/?p=gorecfile.git;a=blobdiff_plain;f=r.go;h=195a7256aa9ad0f9d276b9f39ad79c956c162c60;hp=ca9bba8316c63b248bcc2eacb648e50db564f427;hb=HEAD;hpb=f9f1568a138310677728de89da321b5b84ccbb7d diff --git a/r.go b/r.go index ca9bba8..a16f847 100644 --- a/r.go +++ b/r.go @@ -1,33 +1,27 @@ -/* -recfile -- GNU recutils'es recfiles parser on pure Go -Copyright (C) 2020 Sergey Matveev +// recfile -- GNU recutils'es recfiles parser on pure Go +// Copyright (C) 2020-2024 Sergey Matveev +// +// This program is free software: you can redistribute it and/or modify +// it under the terms of the GNU General Public License as published by +// the Free Software Foundation, version 3 of the License. +// +// This program is distributed in the hope that it will be useful, +// but WITHOUT ANY WARRANTY; without even the implied warranty of +// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +// GNU General Public License for more details. +// +// You should have received a copy of the GNU General Public License +// along with this program. If not, see . -This program is free software: you can redistribute it and/or modify -it under the terms of the GNU General Public License as published by -the Free Software Foundation, version 3 of the License. - -This program is distributed in the hope that it will be useful, -but WITHOUT ANY WARRANTY; without even the implied warranty of -MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the -GNU General Public License for more details. - -You should have received a copy of the GNU General Public License -along with this program. If not, see . -*/ - -// GNU recutils'es recfiles parser on pure Go package recfile import ( "bufio" "errors" "io" - "regexp" "strings" ) -var KeyValRe = regexp.MustCompile(`([a-zA-Z%][a-zA-Z0-9_]*):\s*(.*)$`) - type Reader struct { scanner *bufio.Scanner } @@ -38,6 +32,31 @@ func NewReader(r io.Reader) *Reader { return &Reader{bufio.NewScanner(r)} } +func getKeyValue(text string) (string, string) { + cols := strings.SplitN(text, ":", 2) + if len(cols) != 2 { + return "", "" + } + k := cols[0] + if len(k) == 0 { + return "", "" + } + if !((k[0] == '%') || + ('a' <= k[0] && k[0] <= 'z') || + ('A' <= k[0] && k[0] <= 'Z')) { + return "", "" + } + for _, c := range k[1:] { + if !((c == '_') || + ('a' <= c && c <= 'z') || + ('A' <= c && c <= 'Z') || + ('0' <= c && c <= '9')) { + return "", "" + } + } + return k, strings.TrimPrefix(cols[1], " ") +} + // Get next record. Each record is just a collection of fields. io.EOF // is returned if there is nothing to read more. func (r *Reader) Next() ([]Field, error) { @@ -59,7 +78,9 @@ func (r *Reader) Next() ([]Field, error) { text = r.scanner.Text() if continuation { - if text[len(text)-1] == '\\' { + if len(text) == 0 { + continuation = false + } else if text[len(text)-1] == '\\' { lines = append(lines, text[:len(text)-1]) } else { lines = append(lines, text) @@ -95,12 +116,10 @@ func (r *Reader) Next() ([]Field, error) { break } - matches := KeyValRe.FindStringSubmatch(text) - if len(matches) == 0 { + name, line = getKeyValue(text) + if name == "" { return fields, errors.New("invalid field format") } - name = matches[1] - line = matches[2] if len(line) > 0 && line[len(line)-1] == '\\' { continuation = true @@ -124,7 +143,7 @@ func (r *Reader) Next() ([]Field, error) { return fields, nil } -// Same as Next(), but creates map from the fields. +// Same as Next(), but with unique keys and last value. func (r *Reader) NextMap() (map[string]string, error) { fields, err := r.Next() if err != nil { @@ -136,3 +155,16 @@ func (r *Reader) NextMap() (map[string]string, error) { } return m, nil } + +// Same as Next(), but with unique keys and slices of values. +func (r *Reader) NextMapWithSlice() (map[string][]string, error) { + fields, err := r.Next() + if err != nil { + return nil, err + } + m := make(map[string][]string) + for _, f := range fields { + m[f.Name] = append(m[f.Name], f.Value) + } + return m, nil +}