From 4be5f7bfb23e363f54aff494e8c6bd77b5937839 Mon Sep 17 00:00:00 2001 From: Philipp Winter Date: Sat, 9 Mar 2024 16:28:23 -0600 Subject: [PATCH] Add new build tool. bibliogra.py requires Python 2, which is a pain to deal with. This commit adds a Go tool that compiles CensorBib from BibTeX to HTML. The tool does the bare minimum and is quite strict in the BibTeX format it expects. --- src/decode.go | 55 ++ src/decode_test.go | 81 +++ src/footer.go | 11 + src/go.mod | 5 + src/go.sum | 2 + src/header.go | 231 +++++++ src/html.go | 130 ++++ src/main.go | 113 +++ src/main_test.go | 43 ++ .../github.com/nickng/bibtex/.gitignore | 24 + src/vendor/github.com/nickng/bibtex/LICENSE | 201 ++++++ src/vendor/github.com/nickng/bibtex/README.md | 17 + src/vendor/github.com/nickng/bibtex/bibtex.go | 355 ++++++++++ src/vendor/github.com/nickng/bibtex/bibtex.y | 89 +++ .../github.com/nickng/bibtex/bibtex.y.go | 645 ++++++++++++++++++ src/vendor/github.com/nickng/bibtex/docs.go | 23 + src/vendor/github.com/nickng/bibtex/error.go | 23 + src/vendor/github.com/nickng/bibtex/lexer.go | 38 ++ .../github.com/nickng/bibtex/scanner.go | 237 +++++++ src/vendor/github.com/nickng/bibtex/token.go | 55 ++ src/vendor/modules.txt | 3 + 21 files changed, 2381 insertions(+) create mode 100644 src/decode.go create mode 100644 src/decode_test.go create mode 100644 src/footer.go create mode 100644 src/go.mod create mode 100644 src/go.sum create mode 100644 src/header.go create mode 100644 src/html.go create mode 100644 src/main.go create mode 100644 src/main_test.go create mode 100644 src/vendor/github.com/nickng/bibtex/.gitignore create mode 100644 src/vendor/github.com/nickng/bibtex/LICENSE create mode 100644 src/vendor/github.com/nickng/bibtex/README.md create mode 100644 src/vendor/github.com/nickng/bibtex/bibtex.go create mode 100644 src/vendor/github.com/nickng/bibtex/bibtex.y create mode 100644 src/vendor/github.com/nickng/bibtex/bibtex.y.go create mode 100644 src/vendor/github.com/nickng/bibtex/docs.go create mode 100644 src/vendor/github.com/nickng/bibtex/error.go create mode 100644 src/vendor/github.com/nickng/bibtex/lexer.go create mode 100644 src/vendor/github.com/nickng/bibtex/scanner.go create mode 100644 src/vendor/github.com/nickng/bibtex/token.go create mode 100644 src/vendor/modules.txt diff --git a/src/decode.go b/src/decode.go new file mode 100644 index 0000000..53cebe4 --- /dev/null +++ b/src/decode.go @@ -0,0 +1,55 @@ +package main + +import ( + "log" + "strings" +) + +type conversion struct { + from string + to string +} + +func decodeTitle(title string) string { + for _, convert := range []conversion{ + {`\#`, "#"}, + {`--`, `–`}, + {"``", "“"}, + {"''", "”"}, + {"'", "’"}, // U+2019 + {`$\cdot$`, `·`}, // U+00B7. + } { + title = strings.Replace(title, convert.from, convert.to, -1) + } + + // Get rid of all curly brackets. We're displaying titles without changing + // their casing. + title = strings.ReplaceAll(title, "{", "") + title = strings.ReplaceAll(title, "}", "") + + return title +} + +func decodeAuthors(authors string) string { + for _, convert := range []conversion{ + {"'", "’"}, + } { + authors = strings.Replace(authors, convert.from, convert.to, -1) + } + // For simplicity, we expect authors to be formatted as "John Doe" instead + // of "Doe, John". + if strings.Contains(authors, ",") { + log.Fatalf("author %q contains a comma", authors) + } + authorSlice := strings.Split(authors, " and ") + return strings.Join(authorSlice, ", ") +} + +func decodeProceedings(proceedings string) string { + for _, convert := range []conversion{ + {`\&`, "&"}, + } { + proceedings = strings.Replace(proceedings, convert.from, convert.to, -1) + } + return proceedings +} diff --git a/src/decode_test.go b/src/decode_test.go new file mode 100644 index 0000000..8276555 --- /dev/null +++ b/src/decode_test.go @@ -0,0 +1,81 @@ +package main + +import ( + "testing" +) + +func TestToString(t *testing.T) { + testCases := []conversion{ + { + from: "Title", + to: "Title", + }, + { + from: "This is a {Title}", + to: "This is a Title", + }, + { + from: "This is a {Title}", + to: "This is a Title", + }, + { + from: `{\#h00t}: Censorship Resistant Microblogging`, + to: `#h00t: Censorship Resistant Microblogging`, + }, + { + from: "``Good'' Worms and Human Rights", + to: "“Good” Worms and Human Rights", + }, + { + from: "An Analysis of {China}'s ``{Great Cannon}''", + to: "An Analysis of China’s “Great Cannon”", + }, + { + from: `lib$\cdot$erate, (n):`, + to: `lib·erate, (n):`, + }, + { + from: "Well -- Exploring the {Great} {Firewall}'s Poisoned {DNS}", + to: "Well – Exploring the Great Firewall’s Poisoned DNS", + }, + } + + for _, test := range testCases { + to := decodeTitle(test.from) + if to != test.to { + t.Errorf("Expected\n%s\ngot\n%s", test.to, to) + } + } +} + +func TestDecodeAuthors(t *testing.T) { + testCases := []conversion{ + { // Multiple authors should be separated by commas. + from: "John Doe and Jane Doe", + to: "John Doe, Jane Doe", + }, + { // Single authors should remain as-is. + from: "John Doe", + to: "John Doe", + }, + { // Single-name authors should remain as-is. + from: "John and Jane", + to: "John, Jane", + }, + { // Non-ASCII characters should be unaffected. + from: "Jóhn Doe", + to: "Jóhn Doe", + }, + { // Apostrophes should be replaced with the right single quote. + from: "John O'Brian", + to: "John O’Brian", + }, + } + + for _, test := range testCases { + to := decodeAuthors(test.from) + if to != test.to { + t.Errorf("Expected\n%s\ngot\n%s", test.to, to) + } + } +} diff --git a/src/footer.go b/src/footer.go new file mode 100644 index 0000000..796c9e1 --- /dev/null +++ b/src/footer.go @@ -0,0 +1,11 @@ +package main + +func footer() string { + return ` + + +` +} diff --git a/src/go.mod b/src/go.mod new file mode 100644 index 0000000..3f4fb15 --- /dev/null +++ b/src/go.mod @@ -0,0 +1,5 @@ +module censorbib-go + +go 1.21.3 + +require github.com/nickng/bibtex v1.3.0 diff --git a/src/go.sum b/src/go.sum new file mode 100644 index 0000000..44be713 --- /dev/null +++ b/src/go.sum @@ -0,0 +1,2 @@ +github.com/nickng/bibtex v1.3.0 h1:iv0408z8Xe+FEVquJUo8eraXnhrAF0e+2/WayPcism8= +github.com/nickng/bibtex v1.3.0/go.mod h1:4BJ3ka/ZjGVXcHOlkzlRonex6U17L3kW6ICEsygP2bg= diff --git a/src/header.go b/src/header.go new file mode 100644 index 0000000..0376f86 --- /dev/null +++ b/src/header.go @@ -0,0 +1,231 @@ +package main + +import ( + "bytes" + "log" + "text/template" + "time" +) + +const headerTemplate = ` + + + + + + The Internet censorship bibliography + + + + + + +
+ +
+ +
+

Selected Research Papers
in Internet Censorship

+
+ +
+ +
+ CensorBib is an online archive of selected research papers in the field + of Internet censorship. Most papers on CensorBib approach the topic + from a technical angle, by proposing designs that circumvent censorship + systems, or by measuring how censorship works. The icons next to each + paper make it easy to download, cite, and link to papers. If you think + I missed a paper, + let me know. + You can sort papers by + year, + reverse year (default), + author, and + reverse author. + Finally, the + net4people/bbs forum + has reading groups for many of the papers listed below. +
+ + + +
+ +
+ +
+ +
+
+
+ +
+ Are you a researcher? If so, you may like my book + Research Power Tools. +
+
+ +
+ +
` + +func header() string { + tmpl, err := template.New("header").Parse(headerTemplate) + if err != nil { + log.Fatal(err) + } + i := struct { + Date string + }{ + Date: time.Now().UTC().Format(time.DateOnly), + } + buf := bytes.NewBufferString("") + if err = tmpl.Execute(buf, i); err != nil { + log.Fatalf("Error executing template: %v", err) + } + return buf.String() +} diff --git a/src/html.go b/src/html.go new file mode 100644 index 0000000..623d484 --- /dev/null +++ b/src/html.go @@ -0,0 +1,130 @@ +package main + +import ( + "fmt" + "io" + "sort" + "strings" + + "github.com/nickng/bibtex" +) + +func sortByYear(yearToEntries map[string][]string) []string { + keys := make([]string, 0, len(yearToEntries)) + for k := range yearToEntries { + keys = append(keys, k) + } + sort.Sort(sort.Reverse(sort.StringSlice(keys))) + return keys +} + +func appendIfNotEmpty(slice []string, s string) []string { + if s != "" { + return append(slice, s) + } + return slice +} + +func makeBib(to io.Writer, bibEntries []bibEntry) { + yearToEntries := make(map[string][]string) + + for _, entry := range bibEntries { + y := entry.Fields["year"].String() + yearToEntries[y] = append(yearToEntries[y], makeBibEntry(&entry)) + } + + sortedYears := sortByYear(yearToEntries) + for _, year := range sortedYears { + fmt.Fprintln(to, "") + } +} + +func makeBibEntry(entry *bibEntry) string { + s := []string{ + fmt.Sprintf("
  • ", entry.CiteName), + `
    `, + makeBibEntryTitle(entry), + `
    `, + `
    `, + makeBibEntryAuthors(entry), + `
    `, + ``, + makeBibEntryMisc(entry), + ``, + `
    • `, + } + return strings.Join(s, "\n") +} + +func makeBibEntryTitle(entry *bibEntry) string { + // Paper title is on the left side. + title := []string{ + ``, + decodeTitle(entry.Fields["title"].String()), + ``, + } + // Icons are on the right side. + icons := []string{ + ``, + fmt.Sprintf("", entry.Fields["url"].String()), + `Download icon`, + ``, + fmt.Sprintf("", entry.CiteName), + `Cached download icon`, + ``, + fmt.Sprintf("", entry.lineNum), + `BibTeX download icon`, + ``, + fmt.Sprintf("", entry.CiteName), + `Paper link icon`, + ``, + ``, + } + return strings.Join(append(title, icons...), "\n") +} + +func makeBibEntryAuthors(entry *bibEntry) string { + s := []string{ + ``, + decodeAuthors(entry.Fields["author"].String()), + ``, + } + return strings.Join(s, "\n") +} + +func makeBibEntryMisc(entry *bibEntry) string { + s := []string{} + s = appendIfNotEmpty(s, makeBibEntryVenue(entry)) + s = appendIfNotEmpty(s, toStr(entry.Fields["year"])) + s = appendIfNotEmpty(s, toStr(entry.Fields["publisher"])) + return strings.Join(s, ", ") +} + +func makeBibEntryVenue(entry *bibEntry) string { + var ( + prefix string + bs bibtex.BibString + ok bool + ) + + if bs, ok = entry.Fields["booktitle"]; ok { + prefix = "In Proc. of: " + } else if bs, ok = entry.Fields["journal"]; ok { + prefix = "In: " + } else { + return "" // Some entries are self-published. + } + + s := []string{ + prefix, + ``, + decodeProceedings(toStr(bs)), + ``, + } + + return strings.Join(s, "") +} diff --git a/src/main.go b/src/main.go new file mode 100644 index 0000000..893db24 --- /dev/null +++ b/src/main.go @@ -0,0 +1,113 @@ +package main + +import ( + "bufio" + "flag" + "fmt" + "io" + "log" + "os" + "regexp" + "strings" + + "github.com/nickng/bibtex" +) + +// Matches e.g.: @inproceedings{Doe2024a, +var re = regexp.MustCompile(`@[a-z]*\{([A-Za-z\-]*[0-9]{4}[a-z]),`) + +// Map a cite name (e.g., Doe2024a) to its line number in the .bib file. All +// cite names are unique. +type entryToLineFunc func(string) int + +// Augment bibtex.BibEntry with the entry's line number in the .bib file. +type bibEntry struct { + bibtex.BibEntry + lineNum int +} + +func toStr(b bibtex.BibString) string { + if b == nil { + return "" + } + return b.String() +} + +func parseBibFile(path string) []bibEntry { + file, err := os.Open(path) + if err != nil { + log.Fatal(err) + } + bib, err := bibtex.Parse(file) + if err != nil { + log.Fatal(err) + } + + // Augment our BibTeX entries with their respective line numbers in the .bib + // file. This is necessary to create the "Download BibTeX" links. + lineOf := buildEntryToLineFunc(path) + bibEntries := []bibEntry{} + for _, entry := range bib.Entries { + bibEntries = append(bibEntries, bibEntry{ + BibEntry: *entry, + lineNum: lineOf(entry.CiteName), + }) + } + + return bibEntries +} + +func buildEntryToLineFunc(path string) entryToLineFunc { + file, err := os.Open(path) + if err != nil { + log.Fatal(err) + } + + sc := bufio.NewScanner(file) + entryToLine := make(map[string]int) + line := 0 + for sc.Scan() { + line++ + s := sc.Text() + if !strings.HasPrefix(s, "@") { + continue + } + entry := parseCiteName(s) // E.g., Doe2024a + entryToLine[entry] = line + } + if err := sc.Err(); err != nil { + log.Fatalf("scan file error: %v", err) + } + + return func(entry string) int { + if line, ok := entryToLine[entry]; ok { + return line + } + log.Fatalf("could not find line number for cite name: %s", entry) + return -1 + } +} + +func parseCiteName(line string) string { + matches := re.FindStringSubmatch(line) + if len(matches) != 2 { + log.Fatalf("failed to extract cite name of: %s", line) + } + return matches[1] +} + +func run(w io.Writer, bibEntries []bibEntry) { + fmt.Fprint(w, header()) + makeBib(w, bibEntries) + fmt.Fprint(w, footer()) +} + +func main() { + path := flag.String("path", "", "Path to .bib file.") + flag.Parse() + if *path == "" { + log.Fatal("No path to .bib file provided.") + } + run(os.Stdout, parseBibFile(*path)) + log.Println("Successfully created bibliography.") +} diff --git a/src/main_test.go b/src/main_test.go new file mode 100644 index 0000000..bd4929f --- /dev/null +++ b/src/main_test.go @@ -0,0 +1,43 @@ +package main + +import ( + "bytes" + "strings" + "testing" + + "github.com/nickng/bibtex" +) + +func mustParse(t *testing.T, s string) bibEntry { + t.Helper() + bib, err := bibtex.Parse(strings.NewReader(s)) + if err != nil { + t.Fatalf("failed to parse bibtex: %v", err) + } + return bibEntry{ + BibEntry: *bib.Entries[0], + lineNum: 0, + } +} + +func TestRun(t *testing.T) { + buf := bytes.NewBufferString("") + entry := mustParse(t, `@inproceedings{Almutairi2024a, + author = {Sultan Almutairi and Yogev Neumann and Khaled Harfoush}, + title = {Fingerprinting {VPNs} with Custom Router Firmware: A New Censorship Threat Model}, + booktitle = {Consumer Communications \& Networking Conference}, + publisher = {IEEE}, + year = {2024}, + url = {https://censorbib.nymity.ch/pdf/Almutairi2024a.pdf}, + }`) + + makeBib(buf, []bibEntry{entry}) + + bufStr := buf.String() + if !strings.HasPrefix(bufStr, " but got %q", bufStr[len(bufStr)-10:]) + } +} diff --git a/src/vendor/github.com/nickng/bibtex/.gitignore b/src/vendor/github.com/nickng/bibtex/.gitignore new file mode 100644 index 0000000..daf913b --- /dev/null +++ b/src/vendor/github.com/nickng/bibtex/.gitignore @@ -0,0 +1,24 @@ +# Compiled Object files, Static and Dynamic libs (Shared Objects) +*.o +*.a +*.so + +# Folders +_obj +_test + +# Architecture specific extensions/prefixes +*.[568vq] +[568vq].out + +*.cgo1.go +*.cgo2.c +_cgo_defun.c +_cgo_gotypes.go +_cgo_export.* + +_testmain.go + +*.exe +*.test +*.prof diff --git a/src/vendor/github.com/nickng/bibtex/LICENSE b/src/vendor/github.com/nickng/bibtex/LICENSE new file mode 100644 index 0000000..16fe87b --- /dev/null +++ b/src/vendor/github.com/nickng/bibtex/LICENSE @@ -0,0 +1,201 @@ + Apache License + Version 2.0, January 2004 + http://www.apache.org/licenses/ + +TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION + +1. Definitions. + + "License" shall mean the terms and conditions for use, reproduction, + and distribution as defined by Sections 1 through 9 of this document. + + "Licensor" shall mean the copyright owner or entity authorized by + the copyright owner that is granting the License. + + "Legal Entity" shall mean the union of the acting entity and all + other entities that control, are controlled by, or are under common + control with that entity. For the purposes of this definition, + "control" means (i) the power, direct or indirect, to cause the + direction or management of such entity, whether by contract or + otherwise, or (ii) ownership of fifty percent (50%) or more of the + outstanding shares, or (iii) beneficial ownership of such entity. + + "You" (or "Your") shall mean an individual or Legal Entity + exercising permissions granted by this License. + + "Source" form shall mean the preferred form for making modifications, + including but not limited to software source code, documentation + source, and configuration files. + + "Object" form shall mean any form resulting from mechanical + transformation or translation of a Source form, including but + not limited to compiled object code, generated documentation, + and conversions to other media types. + + "Work" shall mean the work of authorship, whether in Source or + Object form, made available under the License, as indicated by a + copyright notice that is included in or attached to the work + (an example is provided in the Appendix below). + + "Derivative Works" shall mean any work, whether in Source or Object + form, that is based on (or derived from) the Work and for which the + editorial revisions, annotations, elaborations, or other modifications + represent, as a whole, an original work of authorship. For the purposes + of this License, Derivative Works shall not include works that remain + separable from, or merely link (or bind by name) to the interfaces of, + the Work and Derivative Works thereof. + + "Contribution" shall mean any work of authorship, including + the original version of the Work and any modifications or additions + to that Work or Derivative Works thereof, that is intentionally + submitted to Licensor for inclusion in the Work by the copyright owner + or by an individual or Legal Entity authorized to submit on behalf of + the copyright owner. For the purposes of this definition, "submitted" + means any form of electronic, verbal, or written communication sent + to the Licensor or its representatives, including but not limited to + communication on electronic mailing lists, source code control systems, + and issue tracking systems that are managed by, or on behalf of, the + Licensor for the purpose of discussing and improving the Work, but + excluding communication that is conspicuously marked or otherwise + designated in writing by the copyright owner as "Not a Contribution." + + "Contributor" shall mean Licensor and any individual or Legal Entity + on behalf of whom a Contribution has been received by Licensor and + subsequently incorporated within the Work. + +2. Grant of Copyright License. Subject to the terms and conditions of + this License, each Contributor hereby grants to You a perpetual, + worldwide, non-exclusive, no-charge, royalty-free, irrevocable + copyright license to reproduce, prepare Derivative Works of, + publicly display, publicly perform, sublicense, and distribute the + Work and such Derivative Works in Source or Object form. + +3. Grant of Patent License. Subject to the terms and conditions of + this License, each Contributor hereby grants to You a perpetual, + worldwide, non-exclusive, no-charge, royalty-free, irrevocable + (except as stated in this section) patent license to make, have made, + use, offer to sell, sell, import, and otherwise transfer the Work, + where such license applies only to those patent claims licensable + by such Contributor that are necessarily infringed by their + Contribution(s) alone or by combination of their Contribution(s) + with the Work to which such Contribution(s) was submitted. If You + institute patent litigation against any entity (including a + cross-claim or counterclaim in a lawsuit) alleging that the Work + or a Contribution incorporated within the Work constitutes direct + or contributory patent infringement, then any patent licenses + granted to You under this License for that Work shall terminate + as of the date such litigation is filed. + +4. Redistribution. You may reproduce and distribute copies of the + Work or Derivative Works thereof in any medium, with or without + modifications, and in Source or Object form, provided that You + meet the following conditions: + + (a) You must give any other recipients of the Work or + Derivative Works a copy of this License; and + + (b) You must cause any modified files to carry prominent notices + stating that You changed the files; and + + (c) You must retain, in the Source form of any Derivative Works + that You distribute, all copyright, patent, trademark, and + attribution notices from the Source form of the Work, + excluding those notices that do not pertain to any part of + the Derivative Works; and + + (d) If the Work includes a "NOTICE" text file as part of its + distribution, then any Derivative Works that You distribute must + include a readable copy of the attribution notices contained + within such NOTICE file, excluding those notices that do not + pertain to any part of the Derivative Works, in at least one + of the following places: within a NOTICE text file distributed + as part of the Derivative Works; within the Source form or + documentation, if provided along with the Derivative Works; or, + within a display generated by the Derivative Works, if and + wherever such third-party notices normally appear. The contents + of the NOTICE file are for informational purposes only and + do not modify the License. You may add Your own attribution + notices within Derivative Works that You distribute, alongside + or as an addendum to the NOTICE text from the Work, provided + that such additional attribution notices cannot be construed + as modifying the License. + + You may add Your own copyright statement to Your modifications and + may provide additional or different license terms and conditions + for use, reproduction, or distribution of Your modifications, or + for any such Derivative Works as a whole, provided Your use, + reproduction, and distribution of the Work otherwise complies with + the conditions stated in this License. + +5. Submission of Contributions. Unless You explicitly state otherwise, + any Contribution intentionally submitted for inclusion in the Work + by You to the Licensor shall be under the terms and conditions of + this License, without any additional terms or conditions. + Notwithstanding the above, nothing herein shall supersede or modify + the terms of any separate license agreement you may have executed + with Licensor regarding such Contributions. + +6. Trademarks. This License does not grant permission to use the trade + names, trademarks, service marks, or product names of the Licensor, + except as required for reasonable and customary use in describing the + origin of the Work and reproducing the content of the NOTICE file. + +7. Disclaimer of Warranty. Unless required by applicable law or + agreed to in writing, Licensor provides the Work (and each + Contributor provides its Contributions) on an "AS IS" BASIS, + WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or + implied, including, without limitation, any warranties or conditions + of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A + PARTICULAR PURPOSE. You are solely responsible for determining the + appropriateness of using or redistributing the Work and assume any + risks associated with Your exercise of permissions under this License. + +8. Limitation of Liability. In no event and under no legal theory, + whether in tort (including negligence), contract, or otherwise, + unless required by applicable law (such as deliberate and grossly + negligent acts) or agreed to in writing, shall any Contributor be + liable to You for damages, including any direct, indirect, special, + incidental, or consequential damages of any character arising as a + result of this License or out of the use or inability to use the + Work (including but not limited to damages for loss of goodwill, + work stoppage, computer failure or malfunction, or any and all + other commercial damages or losses), even if such Contributor + has been advised of the possibility of such damages. + +9. Accepting Warranty or Additional Liability. While redistributing + the Work or Derivative Works thereof, You may choose to offer, + and charge a fee for, acceptance of support, warranty, indemnity, + or other liability obligations and/or rights consistent with this + License. However, in accepting such obligations, You may act only + on Your own behalf and on Your sole responsibility, not on behalf + of any other Contributor, and only if You agree to indemnify, + defend, and hold each Contributor harmless for any liability + incurred by, or claims asserted against, such Contributor by reason + of your accepting any such warranty or additional liability. + +END OF TERMS AND CONDITIONS + +APPENDIX: How to apply the Apache License to your work. + + To apply the Apache License to your work, attach the following + boilerplate notice, with the fields enclosed by brackets "[]" + replaced with your own identifying information. (Don't include + the brackets!) The text should be enclosed in the appropriate + comment syntax for the file format. We also recommend that a + file or class name and description of purpose be included on the + same "printed page" as the copyright notice for easier + identification within third-party archives. + +Copyright [yyyy] [name of copyright owner] + +Licensed under the Apache License, Version 2.0 (the "License"); +you may not use this file except in compliance with the License. +You may obtain a copy of the License at + + http://www.apache.org/licenses/LICENSE-2.0 + +Unless required by applicable law or agreed to in writing, software +distributed under the License is distributed on an "AS IS" BASIS, +WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. +See the License for the specific language governing permissions and +limitations under the License. diff --git a/src/vendor/github.com/nickng/bibtex/README.md b/src/vendor/github.com/nickng/bibtex/README.md new file mode 100644 index 0000000..0457c7f --- /dev/null +++ b/src/vendor/github.com/nickng/bibtex/README.md @@ -0,0 +1,17 @@ +# bibtex ![Build Status](https://github.com/nickng/bibtex/actions/workflows/test.yml/badge.svg) [![Go Reference](https://pkg.go.dev/badge/github.com/nickng/bibtex.svg)](https://pkg.go.dev/github.com/nickng/bibtex) + +## `nickng/bibtex` is a bibtex parser and library for Go. + +The bibtex format is not standardised, this parser follows the descriptions found +[here](http://maverick.inria.fr/~Xavier.Decoret/resources/xdkbibtex/bibtex_summary.html). +Please file any issues with a minimal working example. + +To get: + + go get -u github.com/nickng/bibtex/... + +This will also install `prettybib`, a bibtex pretty printer. +To parse and pretty print a bibtex file, for example: + + cd $GOPATH/src/github.com/nickng/bibtex + prettybib -in example/simple.bib diff --git a/src/vendor/github.com/nickng/bibtex/bibtex.go b/src/vendor/github.com/nickng/bibtex/bibtex.go new file mode 100644 index 0000000..8de3390 --- /dev/null +++ b/src/vendor/github.com/nickng/bibtex/bibtex.go @@ -0,0 +1,355 @@ +package bibtex + +import ( + "bytes" + "fmt" + "log" + "sort" + "strconv" + "strings" + "text/tabwriter" + "time" +) + +// BibString is a segment of a bib string. +type BibString interface { + RawString() string // Internal representation. + String() string // Displayed string. +} + +// BibVar is a string variable. +type BibVar struct { + Key string // Variable key. + Value BibString // Variable actual value. +} + +// RawString is the internal representation of the variable. +func (v *BibVar) RawString() string { + return v.Key +} + +func (v *BibVar) String() string { + return v.Value.String() +} + +// BibConst is a string constant. +type BibConst string + +// NewBibConst converts a constant string to BibConst. +func NewBibConst(c string) BibConst { + return BibConst(c) +} + +// RawString is the internal representation of the constant (i.e. the string). +func (c BibConst) RawString() string { + return fmt.Sprintf("{%s}", string(c)) +} + +func (c BibConst) String() string { + return string(c) +} + +// BibComposite is a composite string, may contain both variable and string. +type BibComposite []BibString + +// NewBibComposite creates a new composite with one element. +func NewBibComposite(s BibString) *BibComposite { + comp := &BibComposite{} + return comp.Append(s) +} + +// Append adds a BibString to the composite +func (c *BibComposite) Append(s BibString) *BibComposite { + comp := append(*c, s) + return &comp +} + +func (c *BibComposite) String() string { + var buf bytes.Buffer + for _, s := range *c { + buf.WriteString(s.String()) + } + return buf.String() +} + +// RawString returns a raw (bibtex) representation of the composite string. +func (c *BibComposite) RawString() string { + var buf bytes.Buffer + for i, comp := range *c { + if i > 0 { + buf.WriteString(" # ") + } + switch comp := comp.(type) { + case *BibConst: + buf.WriteString(comp.RawString()) + case *BibVar: + buf.WriteString(comp.RawString()) + case *BibComposite: + buf.WriteString(comp.RawString()) + } + } + return buf.String() +} + +// BibEntry is a record of BibTeX record. +type BibEntry struct { + Type string + CiteName string + Fields map[string]BibString +} + +// NewBibEntry creates a new BibTeX entry. +func NewBibEntry(entryType string, citeName string) *BibEntry { + spaceStripper := strings.NewReplacer(" ", "") + cleanedType := strings.ToLower(spaceStripper.Replace(entryType)) + cleanedName := spaceStripper.Replace(citeName) + return &BibEntry{ + Type: cleanedType, + CiteName: cleanedName, + Fields: map[string]BibString{}, + } +} + +// AddField adds a field (key-value) to a BibTeX entry. +func (entry *BibEntry) AddField(name string, value BibString) { + entry.Fields[strings.TrimSpace(name)] = value +} + +// prettyStringConfig controls the formatting/printing behaviour of the BibTex's and BibEntry's PrettyPrint functions +type prettyStringConfig struct { + // priority controls the order in which fields are printed. Keys with lower values are printed earlier. + //See keyOrderToPriorityMap + priority map[string]int +} + +// keyOrderToPriorityMap is a helper function for WithKeyOrder, converting the user facing key order slice +// into the map format that is internally used by the sort function +func keyOrderToPriorityMap(keyOrder []string) map[string]int { + priority := make(map[string]int) + offset := len(keyOrder) + for i, v := range keyOrder { + priority[v] = i - offset + } + return priority +} + +var defaultPrettyStringConfig = prettyStringConfig{priority: keyOrderToPriorityMap([]string{"title", "author", "url"})} + +// PrettyStringOpt allows to change the pretty print format for BibEntry and BibTex +type PrettyStringOpt func(config *prettyStringConfig) + +// WithKeyOrder changes the order in which BibEntry keys are printed to the order in which they appear in keyOrder +func WithKeyOrder(keyOrder []string) PrettyStringOpt { + return func(config *prettyStringConfig) { + config.priority = make(map[string]int) + offset := len(keyOrder) + for i, v := range keyOrder { + config.priority[v] = i - offset + } + } +} + +// prettyStringAppend appends the pretty print string for BibEntry using config to configure the formatting +func (entry *BibEntry) prettyStringAppend(buf *bytes.Buffer, config prettyStringConfig) { + fmt.Fprintf(buf, "@%s{%s,\n", entry.Type, entry.CiteName) + + // Determine key order. + keys := []string{} + for key := range entry.Fields { + keys = append(keys, key) + } + + sort.Slice(keys, func(i, j int) bool { + pi, pj := config.priority[keys[i]], config.priority[keys[j]] + return pi < pj || (pi == pj && keys[i] < keys[j]) + }) + + // Write fields. + tw := tabwriter.NewWriter(buf, 1, 4, 1, ' ', 0) + for _, key := range keys { + value := entry.Fields[key].String() + format := stringformat(value) + fmt.Fprintf(tw, " %s\t=\t"+format+",\n", key, value) + } + tw.Flush() + buf.WriteString("}\n") + +} + +// PrettyString pretty prints a BibEntry +func (entry *BibEntry) PrettyString(options ...PrettyStringOpt) string { + config := defaultPrettyStringConfig + for _, option := range options { + option(&config) + } + var buf bytes.Buffer + entry.prettyStringAppend(&buf, config) + + return buf.String() +} + +// String returns a BibTex entry as a simplified BibTex string. +func (entry *BibEntry) String() string { + var bibtex bytes.Buffer + bibtex.WriteString(fmt.Sprintf("@%s{%s,\n", entry.Type, entry.CiteName)) + for key, val := range entry.Fields { + if i, err := strconv.Atoi(strings.TrimSpace(val.String())); err == nil { + bibtex.WriteString(fmt.Sprintf(" %s = %d,\n", key, i)) + } else { + bibtex.WriteString(fmt.Sprintf(" %s = {%s},\n", key, strings.TrimSpace(val.String()))) + } + } + bibtex.Truncate(bibtex.Len() - 2) + bibtex.WriteString(fmt.Sprintf("\n}\n")) + return bibtex.String() +} + +// RawString returns a BibTex entry data structure in its internal representation. +func (entry *BibEntry) RawString() string { + var bibtex bytes.Buffer + bibtex.WriteString(fmt.Sprintf("@%s{%s,\n", entry.Type, entry.CiteName)) + for key, val := range entry.Fields { + if i, err := strconv.Atoi(strings.TrimSpace(val.String())); err == nil { + bibtex.WriteString(fmt.Sprintf(" %s = %d,\n", key, i)) + } else { + bibtex.WriteString(fmt.Sprintf(" %s = %s,\n", key, val.RawString())) + } + } + bibtex.Truncate(bibtex.Len() - 2) + bibtex.WriteString(fmt.Sprintf("\n}\n")) + return bibtex.String() +} + +// BibTex is a list of BibTeX entries. +type BibTex struct { + Preambles []BibString // List of Preambles + Entries []*BibEntry // Items in a bibliography. + StringVar map[string]*BibVar // Map from string variable to string. + + // A list of default BibVars that are implicitly + // defined and can be used without defining + defaultVars map[string]string +} + +// NewBibTex creates a new BibTex data structure. +func NewBibTex() *BibTex { + // Sets up some default vars + months := map[string]time.Month{ + "jan": 1, "feb": 2, "mar": 3, + "apr": 4, "may": 5, "jun": 6, + "jul": 7, "aug": 8, "sep": 9, + "oct": 10, "nov": 11, "dec": 12, + } + + defaultVars := make(map[string]string) + for mth, month := range months { + // TODO(nickng): i10n of month name in user's local language + defaultVars[mth] = month.String() + } + + return &BibTex{ + Preambles: []BibString{}, + Entries: []*BibEntry{}, + StringVar: make(map[string]*BibVar), + + defaultVars: defaultVars, + } +} + +// AddPreamble adds a preamble to a bibtex. +func (bib *BibTex) AddPreamble(p BibString) { + bib.Preambles = append(bib.Preambles, p) +} + +// AddEntry adds an entry to the BibTeX data structure. +func (bib *BibTex) AddEntry(entry *BibEntry) { + bib.Entries = append(bib.Entries, entry) +} + +// AddStringVar adds a new string var (if does not exist). +func (bib *BibTex) AddStringVar(key string, val BibString) { + bib.StringVar[key] = &BibVar{Key: key, Value: val} +} + +// GetStringVar looks up a string by its key. +func (bib *BibTex) GetStringVar(key string) *BibVar { + if bv, ok := bib.StringVar[key]; ok { + return bv + } + if v, ok := bib.getDefaultVar(key); ok { + return v + } + // This is undefined. + log.Fatalf("%s: %s", ErrUnknownStringVar, key) + return nil +} + +// getDefaultVar is a fallback for looking up keys (e.g. 3-character month) +// and use them even though it hasn't been defined in the bib. +func (bib *BibTex) getDefaultVar(key string) (*BibVar, bool) { + if v, ok := bib.defaultVars[key]; ok { + // if found, add this to the BibTex + bib.StringVar[key] = &BibVar{Key: key, Value: NewBibConst(v)} + return bib.StringVar[key], true + } + + return nil, false +} + +// String returns a BibTex data structure as a simplified BibTex string. +func (bib *BibTex) String() string { + var bibtex bytes.Buffer + for _, entry := range bib.Entries { + bibtex.WriteString(entry.String()) + } + return bibtex.String() +} + +// RawString returns a BibTex data structure in its internal representation. +func (bib *BibTex) RawString() string { + var bibtex bytes.Buffer + for k, strvar := range bib.StringVar { + bibtex.WriteString(fmt.Sprintf("@string{%s = {%s}}\n", k, strvar.String())) + } + for _, preamble := range bib.Preambles { + bibtex.WriteString(fmt.Sprintf("@preamble{%s}\n", preamble.RawString())) + } + for _, entry := range bib.Entries { + bibtex.WriteString(entry.RawString()) + } + return bibtex.String() +} + +// PrettyString pretty prints a BibTex +func (bib *BibTex) PrettyString(options ...PrettyStringOpt) string { + config := defaultPrettyStringConfig + for _, option := range options { + option(&config) + } + + var buf bytes.Buffer + for i, entry := range bib.Entries { + if i != 0 { + fmt.Fprint(&buf, "\n") + } + entry.prettyStringAppend(&buf, config) + + } + return buf.String() +} + +// stringformat determines the correct formatting verb for the given BibTeX field value. +func stringformat(v string) string { + // Numbers may be represented unquoted. + if _, err := strconv.Atoi(v); err == nil { + return "%s" + } + + // Strings with certain characters must be brace quoted. + if strings.ContainsAny(v, "\"{}") { + return "{%s}" + } + + // Default to quoted string. + return "%q" +} diff --git a/src/vendor/github.com/nickng/bibtex/bibtex.y b/src/vendor/github.com/nickng/bibtex/bibtex.y new file mode 100644 index 0000000..2664cb0 --- /dev/null +++ b/src/vendor/github.com/nickng/bibtex/bibtex.y @@ -0,0 +1,89 @@ +%{ +package bibtex + +import ( + "io" +) + +type bibTag struct { + key string + val BibString +} + +var bib *BibTex // Only for holding current bib +%} + +%union { + bibtex *BibTex + strval string + bibentry *BibEntry + bibtag *bibTag + bibtags []*bibTag + strings BibString +} + +%token tCOMMENT tSTRING tPREAMBLE +%token tATSIGN tCOLON tEQUAL tCOMMA tPOUND tLBRACE tRBRACE tDQUOTE tLPAREN tRPAREN +%token tBAREIDENT tIDENT tCOMMENTBODY +%type bibtex +%type bibentry +%type tag stringentry +%type tags +%type longstring preambleentry + +%% + +top : bibtex { } + ; + +bibtex : /* empty */ { $$ = NewBibTex(); bib = $$ } + | bibtex bibentry { $$ = $1; $$.AddEntry($2) } + | bibtex commententry { $$ = $1 } + | bibtex stringentry { $$ = $1; $$.AddStringVar($2.key, $2.val) } + | bibtex preambleentry { $$ = $1; $$.AddPreamble($2) } + ; + +bibentry : tATSIGN tBAREIDENT tLBRACE tBAREIDENT tCOMMA tags tRBRACE { $$ = NewBibEntry($2, $4); for _, t := range $6 { $$.AddField(t.key, t.val) } } + | tATSIGN tBAREIDENT tLPAREN tBAREIDENT tCOMMA tags tRPAREN { $$ = NewBibEntry($2, $4); for _, t := range $6 { $$.AddField(t.key, t.val) } } + ; + +commententry : tATSIGN tCOMMENT tCOMMENTBODY { } + ; + +stringentry : tATSIGN tSTRING tLBRACE tBAREIDENT tEQUAL longstring tRBRACE { $$ = &bibTag{key: $4, val: $6 } } + | tATSIGN tSTRING tLPAREN tBAREIDENT tEQUAL longstring tRBRACE { $$ = &bibTag{key: $4, val: $6 } } + ; + +preambleentry : tATSIGN tPREAMBLE tLBRACE longstring tRBRACE { $$ = $4 } + | tATSIGN tPREAMBLE tLPAREN longstring tRPAREN { $$ = $4 } + ; + +longstring : tIDENT { $$ = NewBibConst($1) } + | tBAREIDENT { $$ = bib.GetStringVar($1) } + | longstring tPOUND tIDENT { $$ = NewBibComposite($1); $$.(*BibComposite).Append(NewBibConst($3))} + | longstring tPOUND tBAREIDENT { $$ = NewBibComposite($1); $$.(*BibComposite).Append(bib.GetStringVar($3)) } + ; + +tag : /* empty */ { } + | tBAREIDENT tEQUAL longstring { $$ = &bibTag{key: $1, val: $3} } + ; + +tags : tag { if $1 != nil { $$ = []*bibTag{$1}; } } + | tags tCOMMA tag { if $3 == nil { $$ = $1 } else { $$ = append($1, $3) } } + ; + +%% + +// Parse is the entry point to the bibtex parser. +func Parse(r io.Reader) (*BibTex, error) { + l := newLexer(r) + bibtexParse(l) + switch { + case len(l.Errors) > 0: // Non-yacc errors + return nil, l.Errors[0] + case len(l.ParseErrors) > 0: + return nil, l.ParseErrors[0] + default: + return bib, nil + } +} diff --git a/src/vendor/github.com/nickng/bibtex/bibtex.y.go b/src/vendor/github.com/nickng/bibtex/bibtex.y.go new file mode 100644 index 0000000..a394cb3 --- /dev/null +++ b/src/vendor/github.com/nickng/bibtex/bibtex.y.go @@ -0,0 +1,645 @@ +// Code generated by goyacc -p bibtex -o bibtex.y.go bibtex.y. DO NOT EDIT. + +//line bibtex.y:2 +package bibtex + +import __yyfmt__ "fmt" + +//line bibtex.y:2 + +import ( + "io" +) + +type bibTag struct { + key string + val BibString +} + +var bib *BibTex // Only for holding current bib + +//line bibtex.y:16 +type bibtexSymType struct { + yys int + bibtex *BibTex + strval string + bibentry *BibEntry + bibtag *bibTag + bibtags []*bibTag + strings BibString +} + +const tCOMMENT = 57346 +const tSTRING = 57347 +const tPREAMBLE = 57348 +const tATSIGN = 57349 +const tCOLON = 57350 +const tEQUAL = 57351 +const tCOMMA = 57352 +const tPOUND = 57353 +const tLBRACE = 57354 +const tRBRACE = 57355 +const tDQUOTE = 57356 +const tLPAREN = 57357 +const tRPAREN = 57358 +const tBAREIDENT = 57359 +const tIDENT = 57360 +const tCOMMENTBODY = 57361 + +var bibtexToknames = [...]string{ + "$end", + "error", + "$unk", + "tCOMMENT", + "tSTRING", + "tPREAMBLE", + "tATSIGN", + "tCOLON", + "tEQUAL", + "tCOMMA", + "tPOUND", + "tLBRACE", + "tRBRACE", + "tDQUOTE", + "tLPAREN", + "tRPAREN", + "tBAREIDENT", + "tIDENT", + "tCOMMENTBODY", +} +var bibtexStatenames = [...]string{} + +const bibtexEofCode = 1 +const bibtexErrCode = 2 +const bibtexInitialStackSize = 16 + +//line bibtex.y:75 + +// Parse is the entry point to the bibtex parser. +func Parse(r io.Reader) (*BibTex, error) { + l := newLexer(r) + bibtexParse(l) + switch { + case len(l.Errors) > 0: // Non-yacc errors + return nil, l.Errors[0] + case len(l.ParseErrors) > 0: + return nil, l.ParseErrors[0] + default: + return bib, nil + } +} + +//line yacctab:1 +var bibtexExca = [...]int{ + -1, 1, + 1, -1, + -2, 0, +} + +const bibtexPrivate = 57344 + +const bibtexLast = 54 + +var bibtexAct = [...]int{ + + 23, 14, 35, 34, 9, 10, 11, 25, 24, 41, + 40, 36, 43, 22, 21, 32, 20, 8, 45, 26, + 33, 17, 19, 15, 18, 12, 16, 32, 13, 47, + 38, 39, 37, 32, 43, 46, 32, 42, 31, 32, + 28, 27, 44, 30, 29, 49, 48, 7, 4, 1, + 6, 5, 3, 2, +} +var bibtexPact = [...]int{ + + -1000, -1000, 40, -1000, -1000, -1000, -1000, 0, 13, -18, + 11, 9, 5, -1, -1000, -3, -4, -10, -10, 31, + 30, 35, 34, 25, -1000, -1000, 4, -6, -6, -10, + -10, -1000, -8, -1000, 24, -1000, 33, 2, 22, 16, + -1000, -1000, -1000, -6, -10, -1000, -1000, -1000, -1000, 28, +} +var bibtexPgo = [...]int{ + + 0, 53, 52, 2, 51, 3, 0, 50, 49, 48, +} +var bibtexR1 = [...]int{ + + 0, 8, 1, 1, 1, 1, 1, 2, 2, 9, + 4, 4, 7, 7, 6, 6, 6, 6, 3, 3, + 5, 5, +} +var bibtexR2 = [...]int{ + + 0, 1, 0, 2, 2, 2, 2, 7, 7, 3, + 7, 7, 5, 5, 1, 1, 3, 3, 0, 3, + 1, 3, +} +var bibtexChk = [...]int{ + + -1000, -8, -1, -2, -9, -4, -7, 7, 17, 4, + 5, 6, 12, 15, 19, 12, 15, 12, 15, 17, + 17, 17, 17, -6, 18, 17, -6, 10, 10, 9, + 9, 13, 11, 16, -5, -3, 17, -5, -6, -6, + 18, 17, 13, 10, 9, 16, 13, 13, -3, -6, +} +var bibtexDef = [...]int{ + + 2, -2, 1, 3, 4, 5, 6, 0, 0, 0, + 0, 0, 0, 0, 9, 0, 0, 0, 0, 0, + 0, 0, 0, 0, 14, 15, 0, 18, 18, 0, + 0, 12, 0, 13, 0, 20, 0, 0, 0, 0, + 16, 17, 7, 18, 0, 8, 10, 11, 21, 19, +} +var bibtexTok1 = [...]int{ + + 1, +} +var bibtexTok2 = [...]int{ + + 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, + 12, 13, 14, 15, 16, 17, 18, 19, +} +var bibtexTok3 = [...]int{ + 0, +} + +var bibtexErrorMessages = [...]struct { + state int + token int + msg string +}{} + +//line yaccpar:1 + +/* parser for yacc output */ + +var ( + bibtexDebug = 0 + bibtexErrorVerbose = false +) + +type bibtexLexer interface { + Lex(lval *bibtexSymType) int + Error(s string) +} + +type bibtexParser interface { + Parse(bibtexLexer) int + Lookahead() int +} + +type bibtexParserImpl struct { + lval bibtexSymType + stack [bibtexInitialStackSize]bibtexSymType + char int +} + +func (p *bibtexParserImpl) Lookahead() int { + return p.char +} + +func bibtexNewParser() bibtexParser { + return &bibtexParserImpl{} +} + +const bibtexFlag = -1000 + +func bibtexTokname(c int) string { + if c >= 1 && c-1 < len(bibtexToknames) { + if bibtexToknames[c-1] != "" { + return bibtexToknames[c-1] + } + } + return __yyfmt__.Sprintf("tok-%v", c) +} + +func bibtexStatname(s int) string { + if s >= 0 && s < len(bibtexStatenames) { + if bibtexStatenames[s] != "" { + return bibtexStatenames[s] + } + } + return __yyfmt__.Sprintf("state-%v", s) +} + +func bibtexErrorMessage(state, lookAhead int) string { + const TOKSTART = 4 + + if !bibtexErrorVerbose { + return "syntax error" + } + + for _, e := range bibtexErrorMessages { + if e.state == state && e.token == lookAhead { + return "syntax error: " + e.msg + } + } + + res := "syntax error: unexpected " + bibtexTokname(lookAhead) + + // To match Bison, suggest at most four expected tokens. + expected := make([]int, 0, 4) + + // Look for shiftable tokens. + base := bibtexPact[state] + for tok := TOKSTART; tok-1 < len(bibtexToknames); tok++ { + if n := base + tok; n >= 0 && n < bibtexLast && bibtexChk[bibtexAct[n]] == tok { + if len(expected) == cap(expected) { + return res + } + expected = append(expected, tok) + } + } + + if bibtexDef[state] == -2 { + i := 0 + for bibtexExca[i] != -1 || bibtexExca[i+1] != state { + i += 2 + } + + // Look for tokens that we accept or reduce. + for i += 2; bibtexExca[i] >= 0; i += 2 { + tok := bibtexExca[i] + if tok < TOKSTART || bibtexExca[i+1] == 0 { + continue + } + if len(expected) == cap(expected) { + return res + } + expected = append(expected, tok) + } + + // If the default action is to accept or reduce, give up. + if bibtexExca[i+1] != 0 { + return res + } + } + + for i, tok := range expected { + if i == 0 { + res += ", expecting " + } else { + res += " or " + } + res += bibtexTokname(tok) + } + return res +} + +func bibtexlex1(lex bibtexLexer, lval *bibtexSymType) (char, token int) { + token = 0 + char = lex.Lex(lval) + if char <= 0 { + token = bibtexTok1[0] + goto out + } + if char < len(bibtexTok1) { + token = bibtexTok1[char] + goto out + } + if char >= bibtexPrivate { + if char < bibtexPrivate+len(bibtexTok2) { + token = bibtexTok2[char-bibtexPrivate] + goto out + } + } + for i := 0; i < len(bibtexTok3); i += 2 { + token = bibtexTok3[i+0] + if token == char { + token = bibtexTok3[i+1] + goto out + } + } + +out: + if token == 0 { + token = bibtexTok2[1] /* unknown char */ + } + if bibtexDebug >= 3 { + __yyfmt__.Printf("lex %s(%d)\n", bibtexTokname(token), uint(char)) + } + return char, token +} + +func bibtexParse(bibtexlex bibtexLexer) int { + return bibtexNewParser().Parse(bibtexlex) +} + +func (bibtexrcvr *bibtexParserImpl) Parse(bibtexlex bibtexLexer) int { + var bibtexn int + var bibtexVAL bibtexSymType + var bibtexDollar []bibtexSymType + _ = bibtexDollar // silence set and not used + bibtexS := bibtexrcvr.stack[:] + + Nerrs := 0 /* number of errors */ + Errflag := 0 /* error recovery flag */ + bibtexstate := 0 + bibtexrcvr.char = -1 + bibtextoken := -1 // bibtexrcvr.char translated into internal numbering + defer func() { + // Make sure we report no lookahead when not parsing. + bibtexstate = -1 + bibtexrcvr.char = -1 + bibtextoken = -1 + }() + bibtexp := -1 + goto bibtexstack + +ret0: + return 0 + +ret1: + return 1 + +bibtexstack: + /* put a state and value onto the stack */ + if bibtexDebug >= 4 { + __yyfmt__.Printf("char %v in %v\n", bibtexTokname(bibtextoken), bibtexStatname(bibtexstate)) + } + + bibtexp++ + if bibtexp >= len(bibtexS) { + nyys := make([]bibtexSymType, len(bibtexS)*2) + copy(nyys, bibtexS) + bibtexS = nyys + } + bibtexS[bibtexp] = bibtexVAL + bibtexS[bibtexp].yys = bibtexstate + +bibtexnewstate: + bibtexn = bibtexPact[bibtexstate] + if bibtexn <= bibtexFlag { + goto bibtexdefault /* simple state */ + } + if bibtexrcvr.char < 0 { + bibtexrcvr.char, bibtextoken = bibtexlex1(bibtexlex, &bibtexrcvr.lval) + } + bibtexn += bibtextoken + if bibtexn < 0 || bibtexn >= bibtexLast { + goto bibtexdefault + } + bibtexn = bibtexAct[bibtexn] + if bibtexChk[bibtexn] == bibtextoken { /* valid shift */ + bibtexrcvr.char = -1 + bibtextoken = -1 + bibtexVAL = bibtexrcvr.lval + bibtexstate = bibtexn + if Errflag > 0 { + Errflag-- + } + goto bibtexstack + } + +bibtexdefault: + /* default state action */ + bibtexn = bibtexDef[bibtexstate] + if bibtexn == -2 { + if bibtexrcvr.char < 0 { + bibtexrcvr.char, bibtextoken = bibtexlex1(bibtexlex, &bibtexrcvr.lval) + } + + /* look through exception table */ + xi := 0 + for { + if bibtexExca[xi+0] == -1 && bibtexExca[xi+1] == bibtexstate { + break + } + xi += 2 + } + for xi += 2; ; xi += 2 { + bibtexn = bibtexExca[xi+0] + if bibtexn < 0 || bibtexn == bibtextoken { + break + } + } + bibtexn = bibtexExca[xi+1] + if bibtexn < 0 { + goto ret0 + } + } + if bibtexn == 0 { + /* error ... attempt to resume parsing */ + switch Errflag { + case 0: /* brand new error */ + bibtexlex.Error(bibtexErrorMessage(bibtexstate, bibtextoken)) + Nerrs++ + if bibtexDebug >= 1 { + __yyfmt__.Printf("%s", bibtexStatname(bibtexstate)) + __yyfmt__.Printf(" saw %s\n", bibtexTokname(bibtextoken)) + } + fallthrough + + case 1, 2: /* incompletely recovered error ... try again */ + Errflag = 3 + + /* find a state where "error" is a legal shift action */ + for bibtexp >= 0 { + bibtexn = bibtexPact[bibtexS[bibtexp].yys] + bibtexErrCode + if bibtexn >= 0 && bibtexn < bibtexLast { + bibtexstate = bibtexAct[bibtexn] /* simulate a shift of "error" */ + if bibtexChk[bibtexstate] == bibtexErrCode { + goto bibtexstack + } + } + + /* the current p has no shift on "error", pop stack */ + if bibtexDebug >= 2 { + __yyfmt__.Printf("error recovery pops state %d\n", bibtexS[bibtexp].yys) + } + bibtexp-- + } + /* there is no state on the stack with an error shift ... abort */ + goto ret1 + + case 3: /* no shift yet; clobber input char */ + if bibtexDebug >= 2 { + __yyfmt__.Printf("error recovery discards %s\n", bibtexTokname(bibtextoken)) + } + if bibtextoken == bibtexEofCode { + goto ret1 + } + bibtexrcvr.char = -1 + bibtextoken = -1 + goto bibtexnewstate /* try again in the same state */ + } + } + + /* reduction by production bibtexn */ + if bibtexDebug >= 2 { + __yyfmt__.Printf("reduce %v in:\n\t%v\n", bibtexn, bibtexStatname(bibtexstate)) + } + + bibtexnt := bibtexn + bibtexpt := bibtexp + _ = bibtexpt // guard against "declared and not used" + + bibtexp -= bibtexR2[bibtexn] + // bibtexp is now the index of $0. Perform the default action. Iff the + // reduced production is ε, $1 is possibly out of range. + if bibtexp+1 >= len(bibtexS) { + nyys := make([]bibtexSymType, len(bibtexS)*2) + copy(nyys, bibtexS) + bibtexS = nyys + } + bibtexVAL = bibtexS[bibtexp+1] + + /* consult goto table to find next state */ + bibtexn = bibtexR1[bibtexn] + bibtexg := bibtexPgo[bibtexn] + bibtexj := bibtexg + bibtexS[bibtexp].yys + 1 + + if bibtexj >= bibtexLast { + bibtexstate = bibtexAct[bibtexg] + } else { + bibtexstate = bibtexAct[bibtexj] + if bibtexChk[bibtexstate] != -bibtexn { + bibtexstate = bibtexAct[bibtexg] + } + } + // dummy call; replaced with literal code + switch bibtexnt { + + case 1: + bibtexDollar = bibtexS[bibtexpt-1 : bibtexpt+1] +//line bibtex.y:36 + { + } + case 2: + bibtexDollar = bibtexS[bibtexpt-0 : bibtexpt+1] +//line bibtex.y:39 + { + bibtexVAL.bibtex = NewBibTex() + bib = bibtexVAL.bibtex + } + case 3: + bibtexDollar = bibtexS[bibtexpt-2 : bibtexpt+1] +//line bibtex.y:40 + { + bibtexVAL.bibtex = bibtexDollar[1].bibtex + bibtexVAL.bibtex.AddEntry(bibtexDollar[2].bibentry) + } + case 4: + bibtexDollar = bibtexS[bibtexpt-2 : bibtexpt+1] +//line bibtex.y:41 + { + bibtexVAL.bibtex = bibtexDollar[1].bibtex + } + case 5: + bibtexDollar = bibtexS[bibtexpt-2 : bibtexpt+1] +//line bibtex.y:42 + { + bibtexVAL.bibtex = bibtexDollar[1].bibtex + bibtexVAL.bibtex.AddStringVar(bibtexDollar[2].bibtag.key, bibtexDollar[2].bibtag.val) + } + case 6: + bibtexDollar = bibtexS[bibtexpt-2 : bibtexpt+1] +//line bibtex.y:43 + { + bibtexVAL.bibtex = bibtexDollar[1].bibtex + bibtexVAL.bibtex.AddPreamble(bibtexDollar[2].strings) + } + case 7: + bibtexDollar = bibtexS[bibtexpt-7 : bibtexpt+1] +//line bibtex.y:46 + { + bibtexVAL.bibentry = NewBibEntry(bibtexDollar[2].strval, bibtexDollar[4].strval) + for _, t := range bibtexDollar[6].bibtags { + bibtexVAL.bibentry.AddField(t.key, t.val) + } + } + case 8: + bibtexDollar = bibtexS[bibtexpt-7 : bibtexpt+1] +//line bibtex.y:47 + { + bibtexVAL.bibentry = NewBibEntry(bibtexDollar[2].strval, bibtexDollar[4].strval) + for _, t := range bibtexDollar[6].bibtags { + bibtexVAL.bibentry.AddField(t.key, t.val) + } + } + case 9: + bibtexDollar = bibtexS[bibtexpt-3 : bibtexpt+1] +//line bibtex.y:50 + { + } + case 10: + bibtexDollar = bibtexS[bibtexpt-7 : bibtexpt+1] +//line bibtex.y:53 + { + bibtexVAL.bibtag = &bibTag{key: bibtexDollar[4].strval, val: bibtexDollar[6].strings} + } + case 11: + bibtexDollar = bibtexS[bibtexpt-7 : bibtexpt+1] +//line bibtex.y:54 + { + bibtexVAL.bibtag = &bibTag{key: bibtexDollar[4].strval, val: bibtexDollar[6].strings} + } + case 12: + bibtexDollar = bibtexS[bibtexpt-5 : bibtexpt+1] +//line bibtex.y:57 + { + bibtexVAL.strings = bibtexDollar[4].strings + } + case 13: + bibtexDollar = bibtexS[bibtexpt-5 : bibtexpt+1] +//line bibtex.y:58 + { + bibtexVAL.strings = bibtexDollar[4].strings + } + case 14: + bibtexDollar = bibtexS[bibtexpt-1 : bibtexpt+1] +//line bibtex.y:61 + { + bibtexVAL.strings = NewBibConst(bibtexDollar[1].strval) + } + case 15: + bibtexDollar = bibtexS[bibtexpt-1 : bibtexpt+1] +//line bibtex.y:62 + { + bibtexVAL.strings = bib.GetStringVar(bibtexDollar[1].strval) + } + case 16: + bibtexDollar = bibtexS[bibtexpt-3 : bibtexpt+1] +//line bibtex.y:63 + { + bibtexVAL.strings = NewBibComposite(bibtexDollar[1].strings) + bibtexVAL.strings.(*BibComposite).Append(NewBibConst(bibtexDollar[3].strval)) + } + case 17: + bibtexDollar = bibtexS[bibtexpt-3 : bibtexpt+1] +//line bibtex.y:64 + { + bibtexVAL.strings = NewBibComposite(bibtexDollar[1].strings) + bibtexVAL.strings.(*BibComposite).Append(bib.GetStringVar(bibtexDollar[3].strval)) + } + case 18: + bibtexDollar = bibtexS[bibtexpt-0 : bibtexpt+1] +//line bibtex.y:67 + { + } + case 19: + bibtexDollar = bibtexS[bibtexpt-3 : bibtexpt+1] +//line bibtex.y:68 + { + bibtexVAL.bibtag = &bibTag{key: bibtexDollar[1].strval, val: bibtexDollar[3].strings} + } + case 20: + bibtexDollar = bibtexS[bibtexpt-1 : bibtexpt+1] +//line bibtex.y:71 + { + if bibtexDollar[1].bibtag != nil { + bibtexVAL.bibtags = []*bibTag{bibtexDollar[1].bibtag} + } + } + case 21: + bibtexDollar = bibtexS[bibtexpt-3 : bibtexpt+1] +//line bibtex.y:72 + { + if bibtexDollar[3].bibtag == nil { + bibtexVAL.bibtags = bibtexDollar[1].bibtags + } else { + bibtexVAL.bibtags = append(bibtexDollar[1].bibtags, bibtexDollar[3].bibtag) + } + } + } + goto bibtexstack /* stack new state and value */ +} diff --git a/src/vendor/github.com/nickng/bibtex/docs.go b/src/vendor/github.com/nickng/bibtex/docs.go new file mode 100644 index 0000000..7b2883e --- /dev/null +++ b/src/vendor/github.com/nickng/bibtex/docs.go @@ -0,0 +1,23 @@ +// Package bibtex is a bibtex parser written in Go. +// +// The package contains a simple parser and data structure to represent bibtex +// records. +// +// # Supported syntax +// +// The basic syntax is: +// +// @BIBTYPE{IDENT, +// key1 = word, +// key2 = "quoted", +// key3 = {quoted}, +// } +// +// where BIBTYPE is the type of document (e.g. inproceedings, article, etc.) +// and IDENT is a string identifier. +// +// The bibtex format is not standardised, this parser follows the descriptions +// found in the link below. If there are any problems, please file any issues +// with a minimal working example at the GitHub repository. +// http://maverick.inria.fr/~Xavier.Decoret/resources/xdkbibtex/bibtex_summary.html +package bibtex // import "github.com/nickng/bibtex" diff --git a/src/vendor/github.com/nickng/bibtex/error.go b/src/vendor/github.com/nickng/bibtex/error.go new file mode 100644 index 0000000..5119d74 --- /dev/null +++ b/src/vendor/github.com/nickng/bibtex/error.go @@ -0,0 +1,23 @@ +package bibtex + +import ( + "errors" + "fmt" +) + +var ( + // ErrUnexpectedAtsign is an error for unexpected @ in {}. + ErrUnexpectedAtsign = errors.New("unexpected @ sign") + // ErrUnknownStringVar is an error for looking up undefined string var. + ErrUnknownStringVar = errors.New("unknown string variable") +) + +// ErrParse is a parse error. +type ErrParse struct { + Pos tokenPos + Err string // Error string returned from parser. +} + +func (e *ErrParse) Error() string { + return fmt.Sprintf("parse failed at %s: %s", e.Pos, e.Err) +} diff --git a/src/vendor/github.com/nickng/bibtex/lexer.go b/src/vendor/github.com/nickng/bibtex/lexer.go new file mode 100644 index 0000000..4b9d1c6 --- /dev/null +++ b/src/vendor/github.com/nickng/bibtex/lexer.go @@ -0,0 +1,38 @@ +//go:generate goyacc -p bibtex -o bibtex.y.go bibtex.y + +package bibtex + +import ( + "fmt" + "io" +) + +// lexer for bibtex. +type lexer struct { + scanner *scanner + ParseErrors []error // Parse errors from yacc + Errors []error // Other errors +} + +// newLexer returns a new yacc-compatible lexer. +func newLexer(r io.Reader) *lexer { + return &lexer{ + scanner: newScanner(r), + } +} + +// Lex is provided for yacc-compatible parser. +func (l *lexer) Lex(yylval *bibtexSymType) int { + token, strval, err := l.scanner.Scan() + if err != nil { + l.Errors = append(l.Errors, fmt.Errorf("%w at %s", err, l.scanner.pos)) + return int(0) + } + yylval.strval = strval + return int(token) +} + +// Error handles error. +func (l *lexer) Error(err string) { + l.ParseErrors = append(l.ParseErrors, &ErrParse{Err: err, Pos: l.scanner.pos}) +} diff --git a/src/vendor/github.com/nickng/bibtex/scanner.go b/src/vendor/github.com/nickng/bibtex/scanner.go new file mode 100644 index 0000000..73d4f8d --- /dev/null +++ b/src/vendor/github.com/nickng/bibtex/scanner.go @@ -0,0 +1,237 @@ +package bibtex + +import ( + "bufio" + "bytes" + "io" + "strconv" + "strings" +) + +var parseField bool + +// scanner is a lexical scanner +type scanner struct { + commentMode bool + r *bufio.Reader + pos tokenPos +} + +// newScanner returns a new instance of scanner. +func newScanner(r io.Reader) *scanner { + return &scanner{r: bufio.NewReader(r), pos: tokenPos{Char: 0, Lines: []int{}}} +} + +// read reads the next rune from the buffered reader. +// Returns the rune(0) if an error occurs (or io.eof is returned). +func (s *scanner) read() rune { + ch, _, err := s.r.ReadRune() + if err != nil { + return eof + } + if ch == '\n' { + s.pos.Lines = append(s.pos.Lines, s.pos.Char) + s.pos.Char = 0 + } else { + s.pos.Char++ + } + return ch +} + +// unread places the previously read rune back on the reader. +func (s *scanner) unread() { + _ = s.r.UnreadRune() + if s.pos.Char == 0 { + s.pos.Char = s.pos.Lines[len(s.pos.Lines)-1] + s.pos.Lines = s.pos.Lines[:len(s.pos.Lines)-1] + } else { + s.pos.Char-- + } +} + +// Scan returns the next token and literal value. +func (s *scanner) Scan() (tok token, lit string, err error) { + ch := s.read() + if isWhitespace(ch) { + s.ignoreWhitespace() + ch = s.read() + } + if isAlphanum(ch) { + s.unread() + return s.scanIdent() + } + switch ch { + case eof: + return 0, "", nil + case '@': + return tATSIGN, string(ch), nil + case ':': + return tCOLON, string(ch), nil + case ',': + parseField = false // reset parseField if reached end of field. + return tCOMMA, string(ch), nil + case '=': + parseField = true // set parseField if = sign outside quoted or ident. + return tEQUAL, string(ch), nil + case '"': + tok, lit := s.scanQuoted() + return tok, lit, nil + case '{': + if parseField { + return s.scanBraced() + } + // If we're reading a comment, return everything after { + // to the next @-sign (exclusive) + if s.commentMode { + s.unread() + commentBodyTok, commentBody := s.scanCommentBody() + return commentBodyTok, commentBody, nil + } + return tLBRACE, string(ch), nil + case '}': + if parseField { // reset parseField if reached end of entry. + parseField = false + } + return tRBRACE, string(ch), nil + case '#': + return tPOUND, string(ch), nil + case ' ': + s.ignoreWhitespace() + } + return tILLEGAL, string(ch), nil +} + +// scanIdent categorises a string to one of three categories. +func (s *scanner) scanIdent() (tok token, lit string, err error) { + switch ch := s.read(); ch { + case '"': + tok, lit := s.scanQuoted() + return tok, lit, nil + case '{': + return s.scanBraced() + default: + s.unread() // Not open quote/brace. + tok, lit := s.scanBare() + return tok, lit, nil + } +} + +func (s *scanner) scanBare() (token, string) { + var buf bytes.Buffer + for { + if ch := s.read(); ch == eof { + break + } else if !isAlphanum(ch) && !isBareSymbol(ch) || isWhitespace(ch) { + s.unread() + break + } else { + _, _ = buf.WriteRune(ch) + } + } + str := buf.String() + if strings.ToLower(str) == "comment" { + s.commentMode = true + return tCOMMENT, str + } else if strings.ToLower(str) == "preamble" { + return tPREAMBLE, str + } else if strings.ToLower(str) == "string" { + return tSTRING, str + } else if _, err := strconv.Atoi(str); err == nil && parseField { // Special case for numeric + return tIDENT, str + } + return tBAREIDENT, str +} + +// scanBraced parses a braced string, like {this}. +func (s *scanner) scanBraced() (token, string, error) { + var buf bytes.Buffer + var macro bool + brace := 1 + for { + if ch := s.read(); ch == eof { + break + } else if ch == '\\' { + _, _ = buf.WriteRune(ch) + macro = true + } else if ch == '{' { + _, _ = buf.WriteRune(ch) + brace++ + } else if ch == '}' { + brace-- + macro = false + if brace == 0 { // Balances open brace. + return tIDENT, buf.String(), nil + } + _, _ = buf.WriteRune(ch) + } else if ch == '@' { + if macro { + _, _ = buf.WriteRune(ch) + } else { + return token(0), buf.String(), ErrUnexpectedAtsign + } + } else if isWhitespace(ch) { + _, _ = buf.WriteRune(ch) + macro = false + } else { + _, _ = buf.WriteRune(ch) + } + } + return tILLEGAL, buf.String(), nil +} + +// scanQuoted parses a quoted string, like "this". +func (s *scanner) scanQuoted() (token, string) { + var buf bytes.Buffer + brace := 0 + for { + if ch := s.read(); ch == eof { + break + } else if ch == '{' { + brace++ + } else if ch == '}' { + brace-- + } else if ch == '"' { + if brace == 0 { // Matches open quote, unescaped + return tIDENT, buf.String() + } + _, _ = buf.WriteRune(ch) + } else { + _, _ = buf.WriteRune(ch) + } + } + return tILLEGAL, buf.String() +} + +// skipCommentBody is a scan method used for reading bibtex +// comment item by reading all runes until the next @. +// +// e.g. +// @comment{...anything can go here even if braces are unbalanced@ +// comment body string will be "...anything can go here even if braces are unbalanced" +func (s *scanner) scanCommentBody() (token, string) { + var buf bytes.Buffer + for { + if ch := s.read(); ch == eof { + break + } else if ch == '@' { + s.unread() + break + } else { + _, _ = buf.WriteRune(ch) + } + } + s.commentMode = false + return tCOMMENTBODY, buf.String() +} + +// ignoreWhitespace consumes the current rune and all contiguous whitespace. +func (s *scanner) ignoreWhitespace() { + for { + if ch := s.read(); ch == eof { + break + } else if !isWhitespace(ch) { + s.unread() + break + } + } +} diff --git a/src/vendor/github.com/nickng/bibtex/token.go b/src/vendor/github.com/nickng/bibtex/token.go new file mode 100644 index 0000000..17c451e --- /dev/null +++ b/src/vendor/github.com/nickng/bibtex/token.go @@ -0,0 +1,55 @@ +package bibtex + +import ( + "fmt" + "strings" +) + +// Lexer token. +type token int + +const ( + // tILLEGAL stands for an invalid token. + tILLEGAL token = iota +) + +var eof = rune(0) + +// tokenPos is a pair of coordinate to identify start of token. +type tokenPos struct { + Char int + Lines []int +} + +func (p tokenPos) String() string { + return fmt.Sprintf("%d:%d", len(p.Lines)+1, p.Char) +} + +func isWhitespace(ch rune) bool { + return ch == ' ' || ch == '\t' || ch == '\n' || ch == '\r' +} + +func isAlpha(ch rune) bool { + return ('a' <= ch && ch <= 'z') || ('A' <= ch && ch <= 'Z') +} + +func isDigit(ch rune) bool { + return ('0' <= ch && ch <= '9') +} + +func isAlphanum(ch rune) bool { + return isAlpha(ch) || isDigit(ch) +} + +func isBareSymbol(ch rune) bool { + return strings.ContainsRune("-_:./+", ch) +} + +// isSymbol returns true if ch is a valid symbol +func isSymbol(ch rune) bool { + return strings.ContainsRune("!?&*+-./:;<>[]^_`|~@", ch) +} + +func isOpenQuote(ch rune) bool { + return ch == '{' || ch == '"' +} diff --git a/src/vendor/modules.txt b/src/vendor/modules.txt new file mode 100644 index 0000000..f1b35c8 --- /dev/null +++ b/src/vendor/modules.txt @@ -0,0 +1,3 @@ +# github.com/nickng/bibtex v1.3.0 +## explicit; go 1.18 +github.com/nickng/bibtex