Switch to blackfriday, remove Gemtext instructions

https://github.com/pemistahl/lingua-go/discussions/50

LICENSE-2.0

@@ -1,201 +0,0 @@
-                                 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.

README.md

@@ -47,8 +47,8 @@ some of which are enable by default:
 * MathJax is supported (but needs a separte setup)
 
 See the section on
-[extensions](https://github.com/gomarkdown/markdown#extensions) in the
-Markdown library for information on the various extensions.
+[extensions](https://github.com/russross/blackfriday#extensions) in
+the Blackfriday library for information on the various extensions.
 
 A table with footers and a columnspan:
 
@@ -217,8 +217,9 @@ MDCertificateAgreement accepted
 First, it manages the domain, getting the necessary certificates. It
 redirects regular HTTP traffic from port 80 to port 443. It turns on
 the SSL engine for port 443. It redirects `/` to `/view/index` and any
-path that starts with `/view/`, `/edit/`, `/save/` or `/search/` is
-proxied to port 8080 where the Oddmu program can handle it.
+path that starts with `/view/`, `/edit/`, `/save/`, `/add/`,
+`/append/` or `/search/` is proxied to port 8080 where the Oddmu
+program can handle it.
 
 Thus, this is what happens:
 
@@ -265,12 +266,12 @@ To delete remove a user:
 htpasswd -D .htpasswd berta
 ```
 
-Modify your site configuration and protect the `/edit/` and `/save/`
-URLs with a password by adding the following to your `<VirtualHost
-*:443>` section:
+Modify your site configuration and protect the `/edit/`, `/save/`,
+`/add/` and `/append/` URLs with a password by adding the following to
+your `<VirtualHost *:443>` section:
 
 ```apache
-<LocationMatch "^/(edit|save)/">
+<LocationMatch "^/(edit|save|add|append)/">
   AuthType Basic
   AuthName "Password Required"
   AuthUserFile /home/oddmu/.htpasswd
@@ -295,10 +296,9 @@ webserver can read (world readable file, world readable and executable
 directory). Populate it with files.
 
 Make sure that none of the static files look like the wiki paths
-`/view/`, `/edit/`, `/save/` or `/search/`.
-
-For example, create a file called `robots.txt` containing the
-following, tellin all robots that they're not welcome.
+`/view/`, `/edit/`, `/save/`, `/add/`, `/append/` or `/search/`. For
+example, create a file called `robots.txt` containing the following,
+tellin all robots that they're not welcome.
 
 ```text
 User-agent: *
@@ -346,50 +346,8 @@ that matches everything:
 ## Customization (with recompilation)
 
 The Markdown parser can be customized and
-[extensions](https://pkg.go.dev/github.com/gomarkdown/markdown/parser#Extensions)
-can be added. There's an example in the
-[usage](https://github.com/gomarkdown/markdown#usage) section. You'll
-need to make changes to the `viewHandler` yourself.
-
-### Render Gemtext
-
-In a first approximation, Gemtext is valid Markdown except for the
-rocket links (`=>`). Here's how to modify the `loadPage` so that a
-`.gmi` file is loaded if no `.md` is found, and the rocket links are
-translated into Markdown:
-
-```go
-func loadPage(name string) (*Page, error) {
-	filename := name + ".md"
-	body, err := os.ReadFile(filename)
-	if err == nil {
-		return &Page{Title: name, Name: name, Body: body}, nil
-	}
-	filename = name + ".gmi"
-	body, err = os.ReadFile(filename)
-	if err == nil {
-		re := regexp.MustCompile(`(?m)^=>\s*(\S+)\s+(.+)`)
-		body = []byte(re.ReplaceAllString(string(body), `* [$2]($1)`))
-		return &Page{Title: name, Name: name, Body: body}, nil
-	}
-	return nil, err
-}
-```
-
-There is a small problem, however: By default, Markdown expects an
-empty line before a list begins. The following change to `renderHtml`
-uses the `NoEmptyLineBeforeBlock` extension for the parser:
-
-```go
-func (p* Page) renderHtml() {
-    // Here is where a new extension is added!
-	extensions := parser.CommonExtensions | parser.NoEmptyLineBeforeBlock
-	markdownParser := parser.NewWithExtensions(extensions)
-	maybeUnsafeHTML := markdown.ToHTML(p.Body, markdownParser, nil)
-	html := bluemonday.UGCPolicy().SanitizeBytes(maybeUnsafeHTML)
-	p.Html = template.HTML(html);
-}
-```
+[extensions](https://github.com/russross/blackfriday#extensions) can
+be added. You'll need to make changes to `renderHtml` yourself.
 
 ## Understanding search
 
@@ -421,15 +379,15 @@ A document with content "This is a test" when searched with the phrase
 "this test" therefore gets a score of 8: the entire phrase does not
 match but each word gets four points.
 
-Trigrams are sometimes strange: In a text containing the words
-"software" and "#socialmedia", a search for "#software" returns a
-result because the trigram "#so" is part of "#socialmedia".
+Trigrams are sometimes strange: In a text containing the words "main"
+and "rail", a search for "mail" returns a match because the trigrams
+"mai" and "ail" are found. In this situation, the result has a score
+of 0.
 
 ## Limitations
 
 Page titles are filenames with `.md` appended. If your filesystem
-cannot handle it, it can't be a page title. Specifically, *no slashes*
-in filenames.
+cannot handle it, it can't be a page name.
 
 The pages are indexed as the server starts and the index is kept in
 memory. If you have a ton of pages, this surely wastes a lot of

TODO.md

@@ -1,6 +1,3 @@
-Easily prepend or append text for use with a mobile browser. Like
-comments.
-
 Upload files.
 
 Automatically scale or process files.
@@ -9,15 +6,7 @@ Post by Delta Chat? That is, allow certain encrypted emails to post.
 
 Convert the existing wiki.
 
-Investigate how to run a multi-lingual wiki where an appropriate
-template is used based on the language of the page. This is important
-because the template needs to use the appropriate `lang` attribute for
-hyphenation to work.
-
 Investigate how to run a multi-linugual wiki where an appropriate
 version of a page is served based on language preferences of the user.
 This is a low priority issue since it's probably only of interest for
 corporate or governmental sites.
-
-Switch from trigram search to a simple full text search engine?
-https://artem.krylysov.com/blog/2020/07/28/lets-build-a-full-text-search-engine/

add.html

@@ -0,0 +1,21 @@
+<!DOCTYPE html>
+<html>
+  <head>
+    <meta charset="utf-8">
+    <meta name="format-detection" content="telephone=no">
+    <meta name="viewport" content="width=device-width">
+    <title>Add to {{.Title}}</title>
+    <style>
+html { max-width: 70ch; padding: 2ch; margin: auto; color: #111; background: #ffe; }
+form, textarea { width: 100%; }
+    </style>
+  </head>
+  <body>
+    <h1>Adding to {{.Title}}</h1>
+    <form action="/append/{{.Name}}" method="POST">
+      <div><textarea name="body" rows="20" cols="80" placeholder="Text" autofocus></textarea></div>
+      <p><input type="submit" value="Add">
+        <a href="/view/{{.Name}}"><button>Cancel</button></a></p>
+    </form>
+  </body>
+</html>

edit.html

@@ -12,9 +12,10 @@ form, textarea { width: 100%; }
   </head>
   <body>
     <h1>Editing {{.Title}}</h1>
-
     <form action="/save/{{.Name}}" method="POST">
-      <div><textarea name="body" rows="20" cols="80">{{printf "%s" .Body}}</textarea></div>
+      <div><textarea name="body" rows="20" cols="80" placeholder="# Title
+
+Text" autofocus>{{printf "%s" .Body}}</textarea></div>
       <p><input type="submit" value="Save">
         <a href="/view/{{.Name}}"><button>Cancel</button></a></p>
     </form>

filter.go

@@ -1,32 +0,0 @@
-// Copyright 2020  Artem Krylysov
-// Copyright 2023  Alex Schroeder
-//
-// 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.
-//
-// This code was originally copied from
-// https://github.com/akrylysov/simplefts
-// https://artem.krylysov.com/blog/2020/07/28/lets-build-a-full-text-search-engine/
-
-package main
-
-import (
-	"strings"
-)
-
-// lowercaseFilter returns a slice of tokens normalized to lower case.
-func lowercaseFilter(tokens []string) []string {
-	r := make([]string, len(tokens))
-	for i, token := range tokens {
-		r[i] = strings.ToLower(token)
-	}
-	return r
-}

filter_test.go

@@ -1,33 +0,0 @@
-// Copyright 2020  Artem Krylysov
-// Copyright 2023  Alex Schroeder
-//
-// 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.
-//
-// This code was originally copied from
-// https://github.com/akrylysov/simplefts
-// https://artem.krylysov.com/blog/2020/07/28/lets-build-a-full-text-search-engine/
-
-package main
-
-import (
-	"testing"
-
-	"github.com/stretchr/testify/assert"
-)
-
-func TestLowercaseFilter(t *testing.T) {
-	var (
-		in  = []string{"Cat", "DOG", "fish"}
-		out = []string{"cat", "dog", "fish"}
-	)
-	assert.Equal(t, out, lowercaseFilter(in))
-}

go.mod

@@ -4,10 +4,9 @@ go 1.21.0
 
 require (
 	github.com/dgryski/go-trigram v0.0.0-20160407183937-79ec494e1ad0
-	github.com/gomarkdown/markdown v0.0.0-20230716120725-531d2d74bc12
 	github.com/microcosm-cc/bluemonday v1.0.25
 	github.com/pemistahl/lingua-go v1.4.0
-	github.com/stretchr/testify v1.8.4
+	github.com/russross/blackfriday/v2 v2.1.0
 )
 
 require (
@@ -16,6 +15,7 @@ require (
 	github.com/gorilla/css v1.0.0 // indirect
 	github.com/pmezard/go-difflib v1.0.0 // indirect
 	github.com/shopspring/decimal v1.3.1 // indirect
+	github.com/stretchr/testify v1.8.4 // indirect
 	golang.org/x/exp v0.0.0-20221106115401-f9659909a136 // indirect
 	golang.org/x/net v0.12.0 // indirect
 	google.golang.org/protobuf v1.31.0 // indirect

go.sum

@@ -5,9 +5,9 @@ github.com/davecgh/go-spew v1.1.1/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSs
 github.com/dgryski/go-trigram v0.0.0-20160407183937-79ec494e1ad0 h1:b+7JSiBM+hnLQjP/lXztks5hnLt1PS46hktG9VOJgzo=
 github.com/dgryski/go-trigram v0.0.0-20160407183937-79ec494e1ad0/go.mod h1:qzKC/DpcxK67zaSHdCmIv3L9WJViHVinYXN2S7l3RM8=
 github.com/golang/protobuf v1.5.0/go.mod h1:FsONVRAS9T7sI+LIUmWTfcYkHO4aIWwzhcaSAoJOfIk=
-github.com/gomarkdown/markdown v0.0.0-20230716120725-531d2d74bc12 h1:uK3X/2mt4tbSGoHvbLBHUny7CKiuwUip3MArtukol4E=
-github.com/gomarkdown/markdown v0.0.0-20230716120725-531d2d74bc12/go.mod h1:JDGcbDT52eL4fju3sZ4TeHGsQwhG9nbDV21aMyhwPoA=
 github.com/google/go-cmp v0.5.5/go.mod h1:v8dTdLbMG2kIc/vJvl+f65V22dbkXbowE6jgT/gNBxE=
+github.com/google/go-cmp v0.5.8 h1:e6P7q2lk1O+qJJb4BtCQXlK8vWEO8V1ZeuEdJNOqZyg=
+github.com/google/go-cmp v0.5.8/go.mod h1:17dUlkBOakJ0+DkrSSNjCkIjxS6bF9zb3elmeNGIjoY=
 github.com/gorilla/css v1.0.0 h1:BQqNyPTi50JCFMTw/b67hByjMVXZRwGha6wxVGkeihY=
 github.com/gorilla/css v1.0.0/go.mod h1:Dn721qIggHpt4+EFCcTLTU/vk5ySda2ReITrtgBl60c=
 github.com/microcosm-cc/bluemonday v1.0.25 h1:4NEwSfiJ+Wva0VxN5B8OwMicaJvD8r9tlJWm9rtloEg=
@@ -16,6 +16,8 @@ github.com/pemistahl/lingua-go v1.4.0 h1:ifYhthrlW7iO4icdubwlduYnmwU37V1sbNrwhKB
 github.com/pemistahl/lingua-go v1.4.0/go.mod h1:ECuM1Hp/3hvyh7k8aWSqNCPlTxLemFZsRjocUf3KgME=
 github.com/pmezard/go-difflib v1.0.0 h1:4DBwDE0NGyQoBHbLQYPwSUPoCMWR5BEzIk/f1lZbAQM=
 github.com/pmezard/go-difflib v1.0.0/go.mod h1:iKH77koFhYxTK1pcRnkKkqfTogsbg7gZNVY4sRDYZ/4=
+github.com/russross/blackfriday/v2 v2.1.0 h1:JIOH55/0cWyOuilr9/qlrm0BSXldqnqwMsf35Ld67mk=
+github.com/russross/blackfriday/v2 v2.1.0/go.mod h1:+Rmxgy9KzJVeS9/2gXHxylqXiyQDYRxCVz55jmeOWTM=
 github.com/shopspring/decimal v1.3.1 h1:2Usl1nmF/WZucqkFZhnfFYxxxu8LG21F6nPQBE5gKV8=
 github.com/shopspring/decimal v1.3.1/go.mod h1:DKyhrW/HYNuLGql+MJL6WCR6knT2jwCFRcu2hWCYk4o=
 github.com/stretchr/testify v1.8.4 h1:CcVxjf3Q8PM0mHUKJCdn+eZZtm5yQwehR5yeSVQQcUk=

index.go

@@ -1,121 +0,0 @@
-// Copyright 2020  Artem Krylysov
-// Copyright 2023  Alex Schroeder
-//
-// 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.
-//
-// This code was originally copied from
-// https://github.com/akrylysov/simplefts
-// https://artem.krylysov.com/blog/2020/07/28/lets-build-a-full-text-search-engine/
-
-package main
-
-import(
-	"log"
-	"sort"
-)
-
-type docid uint
-
-// next_id is the number of the next document added to the index
-var next_id docid = 0
-
-// index is an inverted index. It maps tokens to document ids. Use add
-// to add a document to the index. Use remove to remove a document
-// from the index. Remove the old document and add the new document to
-// update the index.
-type index map[string][]docid
-
-// add adds a document to the index and returns the new document id.
-// This limits the number of documents and updates that can happen
-// during a particular run.
-func (idx index) add(text string) docid {
-	id := next_id; next_id++
-	for _, token := range analyze(text) {
-		ids := idx[token]
-		if ids != nil && ids[len(ids)-1] == id {
-			// Don't add same ID twice.
-			continue
-		}
-		idx[token] = append(ids, id)
-	}
-	return id
-}
-
-// delete removes a document from the index by removing all the words.
-func (idx index) delete(text string, id docid) {
-	for _, token := range analyze(text) {
-		ids := idx[token]
-		// If the token doesn't show up, that's strange. This
-		// shouldn't happen.
-		if ids == nil {
-			log.Printf("Token %s is not indexed", token)
-			continue
-		}
-		// If the token appears only in this document, remove
-		// the whole entry.
-		if len(ids) == 1 && ids[0] == id {
-			delete(idx, token)
-			continue
-		}
-		// Otherwise, remove the token from the index.
-		i := sort.Search(len(ids), func(i int) bool { return ids[i] >= id })
-		if i != -1 && i < len(ids) && ids[i] == id {
-			copy(ids[i:], ids[i+1:])
-			idx[token] = ids[:len(ids)-1]
-			continue
-		}
-		// If none of the above, then our docid wasn't
-		// indexed. This shouldn't happen, either.
-		log.Printf("The index for token %s does not contain doc id %d", token, id)
-	}
-}
-
-// intersection returns the set intersection between a and b.
-// a and b have to be sorted in ascending order and contain no duplicates.
-func intersection(a []docid, b []docid) []docid {
-	maxLen := len(a)
-	if len(b) > maxLen {
-		maxLen = len(b)
-	}
-	r := make([]docid, 0, maxLen)
-	var i, j int
-	for i < len(a) && j < len(b) {
-		if a[i] < b[j] {
-			i++
-		} else if a[i] > b[j] {
-			j++
-		} else {
-			r = append(r, a[i])
-			i++
-			j++
-		}
-	}
-	return r
-}
-
-// search queries the index for the given text.
-func (idx index) search(text string) []docid {
-	var r []docid
-	for _, token := range analyze(text) {
-		if ids, ok := idx[token]; ok {
-			if r == nil {
-				r = ids
-			} else {
-				r = intersection(r, ids)
-			}
-		} else {
-			// Token doesn't exist.
-			return nil
-		}
-	}
-	return r
-}

index_test.go

@@ -1,41 +0,0 @@
-// Copyright 2020  Artem Krylysov
-// Copyright 2023  Alex Schroeder
-//
-// 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.
-//
-// This code was originally copied from
-// https://github.com/akrylysov/simplefts
-// https://artem.krylysov.com/blog/2020/07/28/lets-build-a-full-text-search-engine/
-
-package main
-
-import (
-	"testing"
-	"github.com/stretchr/testify/assert"
-)
-
-func TestIndex(t *testing.T) {
-	idx := make(index)
-
-	assert.Nil(t, idx.search("foo"))
-	assert.Nil(t, idx.search("donut"))
-
-	id1 := idx.add("A donut on a glass plate. Only the donuts.")
-	assert.Equal(t, idx.search("donut"), []docid{id1})
-	assert.Equal(t, idx.search("DoNuts"), []docid{id1})
-	assert.Equal(t, idx.search("glass"), []docid{id1})
-
-	id2 := idx.add("donut is a donut")
-	assert.Equal(t, idx.search("donut"), []docid{id1, id2})
-	assert.Equal(t, idx.search("DoNuts"), []docid{id1})
-	assert.Equal(t, idx.search("glass"), []docid{id1})
-}

page.go

@@ -3,11 +3,9 @@ package main
 import (
 	"bytes"
 	"fmt"
-	"github.com/gomarkdown/markdown"
-	"github.com/gomarkdown/markdown/ast"
-	"github.com/gomarkdown/markdown/parser"
 	"github.com/microcosm-cc/bluemonday"
 	"github.com/pemistahl/lingua-go"
+	"github.com/russross/blackfriday/v2"
 	"html/template"
 	"os"
 	"path/filepath"
@@ -103,35 +101,39 @@ func (p *Page) handleTitle(replace bool) {
 
 // renderHtml renders the Page.Body to HTML and sets Page.Html.
 func (p *Page) renderHtml() {
-	maybeUnsafeHTML := markdown.ToHTML(p.Body, nil, nil)
+	maybeUnsafeHTML := blackfriday.Run(p.Body)
 	p.Html = sanitizeBytes(maybeUnsafeHTML)
-	p.Language = p.language(p.plainText())
+	p.Language = language(p.plainText())
 }
 
 // plainText renders the Page.Body to plain text and returns it,
 // ignoring all the Markdown and all the newlines. The result is one
 // long single line of text.
 func (p *Page) plainText() string {
-	parser := parser.New()
-	doc := markdown.Parse(p.Body, parser)
+	optList := []blackfriday.Option{blackfriday.WithExtensions(blackfriday.CommonExtensions)}
+	parser := blackfriday.New(optList...)
+	ast := parser.Parse(p.Body)
 	text := []byte("")
-	ast.WalkFunc(doc, func(node ast.Node, entering bool) ast.WalkStatus {
-		if entering && node.AsLeaf() != nil {
-			text = append(text, node.AsLeaf().Literal...)
-			text = append(text, []byte(" ")...)
+	ast.Walk(func(node *blackfriday.Node, entering bool) blackfriday.WalkStatus {
+		if entering && node.Type == blackfriday.Text {
+			s := node.Literal
+			if len(s) == 0 {
+				return blackfriday.GoToNext
+			}
+			// Some Markdown still contains newlines
+			for i, c := range s {
+				if c == '\n' {
+					s[i] = ' '
+				}
+			}
+			if len(text) > 0 && text[len(text)-1] != ' ' && s[0] != ' ' {
+				text = append(text, ' ')
+			}
+
+			text = append(text, s...)
 		}
-		return ast.GoToNext
+		return blackfriday.GoToNext
 	})
-	// Some Markdown still contains newlines
-	for i, c := range text {
-		if c == '\n' {
-			text[i] = ' '
-		}
-	}
-	// Remove trailing space
-	for len(text) > 0 && text[len(text)-1] == ' ' {
-		text = text[0 : len(text)-1]
-	}
 	return string(text)
 }
 
@@ -141,17 +143,12 @@ func (p *Page) summarize(q string) {
 	p.Score = score(q, string(p.Body)) + score(q, p.Title)
 	t := p.plainText()
 	p.Html = sanitize(snippets(q, t))
-	p.Language = p.language(t)
+	p.Language = language(t)
 }
 
-func (p *Page) language(s string) string {
+func language(s string) string {
 	if language, ok := detector.DetectLanguageOf(s); ok {
-		switch language {
-		case lingua.English:
-			return "en"
-		case lingua.German:
-			return "de"
-		}
+		return strings.ToLower(language.IsoCode639_1().String())
 	}
 	return ""
 }

page_test.go

@@ -2,8 +2,9 @@ package main
 
 import (
 	"os"
-	"strings"
+	"regexp"
 	"testing"
+	"github.com/stretchr/testify/assert"
 )
 
 func TestPageTitle(t *testing.T) {
@@ -12,19 +13,10 @@ My back aches for you
 I sit, stare and type for hours
 But yearn for blue sky`)}
 	p.handleTitle(false)
-	if p.Title != "Ache" {
-		t.Logf("The page title was not extracted correctly: %s", p.Title)
-		t.Fail()
-	}
-	if !strings.HasPrefix(string(p.Body), "# Ache") {
-		t.Logf("The page title was removed: %s", p.Body)
-		t.Fail()
-	}
+	assert.Equal(t, "Ache", p.Title)
+	assert.Regexp(t, regexp.MustCompile("^# Ache"), string(p.Body))
 	p.handleTitle(true)
-	if !strings.HasPrefix(string(p.Body), "My back") {
-		t.Logf("The page title was not removed: %s", p.Body)
-		t.Fail()
-	}
+	assert.Regexp(t, regexp.MustCompile("^My back"), string(p.Body))
 }
 
 func TestPagePlainText(t *testing.T) {
@@ -32,12 +24,8 @@ func TestPagePlainText(t *testing.T) {
 The air will not come
 To inhale is an effort
 The summer heat kills`)}
-	s := p.plainText()
 	r := "Water The air will not come To inhale is an effort The summer heat kills"
-	if s != r {
-		t.Logf("The plain text version is wrong: %s", s)
-		t.Fail()
-	}
+	assert.Equal(t, r, p.plainText())
 }
 
 func TestPageHtml(t *testing.T) {
@@ -46,17 +34,13 @@ Silver leaves shine bright
 They droop, boneless, weak and sad
 A cruel sun stares down`)}
 	p.renderHtml()
-	s := string(p.Html)
 	r := `<h1>Sun</h1>
 
 <p>Silver leaves shine bright
 They droop, boneless, weak and sad
 A cruel sun stares down</p>
 `
-	if s != r {
-		t.Logf("The HTML is wrong: %s", s)
-		t.Fail()
-	}
+	assert.Equal(t, r, string(p.Html))
 }
 
 func TestPageDir(t *testing.T) {
@@ -68,11 +52,17 @@ A slow shuffle in the dark
 Moonlight floods the aisle`)}
 	p.save()
 	o, err := loadPage("testdata/moon")
-	if err != nil || string(o.Body) != string(p.Body) {
-		t.Logf("File in subdirectory not loaded: %s", p.Name)
-		t.Fail()
-	}
+	assert.NoError(t, err, "load page")
+	assert.Equal(t, p.Body, o.Body)
 	t.Cleanup(func() {
 		_ = os.RemoveAll("testdata")
 	})
 }
+
+func TestLanguage(t *testing.T) {
+	l := language(`
+My back hurts at night
+My shoulders won't budge today
+Winter bones I say`)
+	assert.Equal(t, "en", l)
+}

search.go

@@ -1,7 +1,8 @@
 package main
 
 import (
-	"log"
+	"fmt"
+	trigram "github.com/dgryski/go-trigram"
 	"io/fs"
 	"path/filepath"
 	"slices"
@@ -10,12 +11,6 @@ import (
 	"unicode/utf8"
 )
 
-// idx is the global full text search index mapping tokens to docids
-var idx index
-
-// documents is an index of document names, i.e. it maps docids to file names in our case
-var docs map[docid]string
-
 // Search is a struct containing the result of a search. Query is the
 // query string and Items is the array of pages with the result.
 // Currently there is no pagination of results! When a page is part of
@@ -26,6 +21,15 @@ type Search struct {
 	Results bool
 }
 
+// index is a struct containing the trigram index for search. It is
+// generated at startup and updated after every page edit. The index
+// is case-insensitive.
+var index trigram.Index
+
+// documents is a map, mapping document ids of the index to page
+// names.
+var documents map[trigram.DocID]string
+
 func indexAdd(path string, info fs.FileInfo, err error) error {
 	if err != nil {
 		return err
@@ -39,43 +43,40 @@ func indexAdd(path string, info fs.FileInfo, err error) error {
 	if err != nil {
 		return err
 	}
-	id := idx.add(string(p.Body))
-	docs[id] = p.Name
+	id := index.Add(strings.ToLower(string(p.Body)))
+	documents[id] = p.Name
 	return nil
 }
 
 func loadIndex() error {
-	idx = make(index)
-	docs = make(map[docid]string)
+	index = make(trigram.Index)
+	documents = make(map[trigram.DocID]string)
 	err := filepath.Walk(".", indexAdd)
 	if err != nil {
-		log.Print("Indexing failed")
-		idx = nil
-		docs = nil
+		fmt.Println("Indexing failed")
+		index = nil
+		documents = nil
 	}
 	return err
 }
 
-// updateIndex deletes the old page from the index before adding the
-// new page, if an old page exists.
 func (p *Page) updateIndex() {
-	var id docid
-	for docId, name := range docs {
+	var id trigram.DocID
+	for docId, name := range documents {
 		if name == p.Name {
 			id = docId
 			break
 		}
 	}
 	if id == 0 {
-		id = idx.add(string(p.Body))
-		docs[id] = p.Name
+		id = index.Add(strings.ToLower(string(p.Body)))
+		documents[id] = p.Name
 	} else {
 		o, err := loadPage(p.Name)
 		if err == nil {
-			idx.delete(string(o.Body), id)
+			index.Delete(strings.ToLower(string(o.Body)), id)
 		}
-		id = idx.add(string(p.Body))
-		docs[id] = p.Name
+		index.Insert(strings.ToLower(string(p.Body)), id)
 	}
 }
 
@@ -85,13 +86,18 @@ func search(q string) []Page {
 	if len(q) == 0 {
 		return make([]Page, 0)
 	}
-	ids := idx.search(q)
+	words := strings.Split(strings.ToLower(q), " ")
+	var trigrams []trigram.T
+	for _, word := range words {
+		trigrams = trigram.Extract(word, trigrams)
+	}
+	ids := index.QueryTrigrams(trigrams)
 	items := make([]Page, len(ids))
 	for i, id := range ids {
-		name := docs[id]
+		name := documents[id]
 		p, err := loadPage(name)
 		if err != nil {
-			log.Printf("Error loading %s", name)
+			fmt.Printf("Error loading %s\n", name)
 		} else {
 			p.summarize(q)
 			items[i] = *p

search_test.go

@@ -9,7 +9,7 @@ import (
 var name string = "test"
 
 // TestIndex relies on README.md being indexed
-func TestSearch(t *testing.T) {
+func TestIndex(t *testing.T) {
 	_ = os.Remove(name + ".md")
 	loadIndex()
 	q := "Oddµ"

snippets_test.go

@@ -2,17 +2,17 @@ package main
 
 import (
 	"testing"
-	"github.com/stretchr/testify/assert"
 )
 
 func TestSnippets(t *testing.T) {
 	s := `We are immersed in a sea of dead people. All the dead that have gone before us, silent now, just staring, gaping. As we move and talk and fret, never once stopping to ask ourselves – or them! – what it was all about. Instead we drown ourselves in noise. Incessantly we babble, surrounded by false friends claiming that all is well. And look at us! Yes, we are well. Patting our backs and expecting a pat – and we do! – we smugly do enjoy.`
 
-	h1 := `We are immersed in a sea of dead people. <b>All</b> the dead that have gone before us, silent now, just … to ask ourselves – or them! – what it was <b>all</b> about. Instead we drown ourselves in no<b>is</b>e. … surrounded by false friends claiming that <b>all</b> <b>is</b> <b>well</b>. And look at us! Yes, we are <b>well</b>. …`
+	h := `We are immersed in a sea of dead people. <b>All</b> the dead that have gone before us, silent now, just … to ask ourselves – or them! – what it was <b>all</b> about. Instead we drown ourselves in no<b>is</b>e. … surrounded by false friends claiming that <b>all</b> <b>is</b> <b>well</b>. And look at us! Yes, we are <b>well</b>. …`
 
-	assert.Equal(t, h1, snippets("all is well", s))
-
-	h2 := `We are immersed in a sea of dead people. All the dead that have gone before us, silent now, just … And look at us! Yes, we are well. Patting our backs and expecting a pat – and we do! – we smugly do <b>enjoy</b>.`
-
-	assert.Equal(t, h2, snippets("enjoy", s))
+	q := "all is well"
+	r := snippets(q, s)
+	if r != h {
+		t.Logf("The snippets are wrong in ｢%s｣", r)
+		t.Fail()
+	}
 }

tokenizer.go

@@ -1,41 +0,0 @@
-// Copyright 2020  Artem Krylysov
-// Copyright 2023  Alex Schroeder
-//
-// 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.
-//
-// This code was originally copied from
-// https://github.com/akrylysov/simplefts
-// https://artem.krylysov.com/blog/2020/07/28/lets-build-a-full-text-search-engine/
-//
-// This file no longer does stemming and stop words.
-
-package main
-
-import (
-	"strings"
-	"unicode"
-)
-
-// tokenize returns a slice of tokens for the given text.
-func tokenize(text string) []string {
-	return strings.FieldsFunc(text, func(r rune) bool {
-		// Split on any character that is not a letter or a number.
-		return !unicode.IsLetter(r) && !unicode.IsNumber(r)
-	})
-}
-
-// analyze analyzes the text and returns a slice of tokens.
-func analyze(text string) []string {
-	tokens := tokenize(text)
-	tokens = lowercaseFilter(tokens)
-	return tokens
-}

tokenizer_test.go

@@ -1,52 +0,0 @@
-// Copyright 2020  Artem Krylysov
-// Copyright 2023  Alex Schroeder
-//
-// 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.
-//
-// This code was originally copied from
-// https://github.com/akrylysov/simplefts
-// https://artem.krylysov.com/blog/2020/07/28/lets-build-a-full-text-search-engine/
-//
-// This file no longer does stemming and stop words.
-
-package main
-
-import (
-	"testing"
-	"github.com/stretchr/testify/assert"
-)
-
-func TestTokenizer(t *testing.T) {
-	testCases := []struct {
-		text   string
-		tokens []string
-	}{
-		{
-			text:   "",
-			tokens: []string{},
-		},
-		{
-			text:   "a",
-			tokens: []string{"a"},
-		},
-		{
-			text:   "small wild,cat!",
-			tokens: []string{"small", "wild", "cat"},
-		},
-	}
-
-	for _, tc := range testCases {
-		t.Run(tc.text, func(st *testing.T) {
-			assert.EqualValues(st, tc.tokens, tokenize(tc.text))
-		})
-	}
-}

view.html

@@ -18,7 +18,8 @@ img { max-width: 100%; }
     <header>
       <a href="#main">Skip navigation</a>
       <a href="/view/index">Home</a>
-      <a href="/edit/{{.Name}}">Edit this page</a>
+      <a href="/edit/{{.Name}}">Edit</a>
+      <a href="/add/{{.Name}}">Add</a>
       <form role="search" action="/search" method="GET">
         <input type="text" spellcheck="false" name="q" required>
         <button>Search</button>

wiki.go

@@ -10,7 +10,8 @@ import (
 )
 
 // Templates are parsed at startup.
-var templates = template.Must(template.ParseFiles("edit.html", "view.html", "search.html"))
+var templates = template.Must(
+	template.ParseFiles("edit.html", "add.html", "view.html", "search.html"))
 
 // validPath is a regular expression where the second group matches a
 // page, so when the handler for "/edit/" is called, a URL path of
@@ -65,7 +66,8 @@ func viewHandler(w http.ResponseWriter, r *http.Request, name string) {
 
 // editHandler uses the "edit.html" template to present an edit page.
 // When editing, the page title is not overriden by a title in the
-// text. Instead, the page name is used.
+// text. Instead, the page name is used. The edit is saved using the
+// saveHandler.
 func editHandler(w http.ResponseWriter, r *http.Request, name string) {
 	p, err := loadPage(name)
 	if err != nil {
@@ -89,6 +91,38 @@ func saveHandler(w http.ResponseWriter, r *http.Request, name string) {
 	http.Redirect(w, r, "/view/"+name, http.StatusFound)
 }
 
+// addHandler uses the "add.html" template to present an empty edit
+// page. What you type there is appended to the page using the
+// appendHandler.
+func addHandler(w http.ResponseWriter, r *http.Request, name string) {
+	p, err := loadPage(name)
+	if err != nil {
+		p = &Page{Title: name, Name: name}
+	} else {
+		p.handleTitle(false)
+	}
+	renderTemplate(w, "add", p)
+}
+
+// appendHandler takes the "body" form parameter and appends it. The
+// browser is redirected to the page view.
+func appendHandler(w http.ResponseWriter, r *http.Request, name string) {
+	body := r.FormValue("body")
+	p, err := loadPage(name)
+	if err != nil {
+		p = &Page{Title: name, Name: name, Body: []byte(body)}
+	} else {
+		p.handleTitle(false)
+		p.Body = append(p.Body, []byte(body)...)
+	}
+	err = p.save()
+	if err != nil {
+		http.Error(w, err.Error(), http.StatusInternalServerError)
+		return
+	}
+	http.Redirect(w, r, "/view/"+name, http.StatusFound)
+}
+
 // makeHandler returns a handler that uses the URL path without the
 // first path element as its argument, e.g. if the URL path is
 // /edit/foo/bar, the editHandler is called with "foo/bar" as its
@@ -115,20 +149,6 @@ func searchHandler(w http.ResponseWriter, r *http.Request) {
 	renderTemplate(w, "search", s)
 }
 
-// searchCommand prints a search result to the command line.
-func searchCommand() {
-	q := strings.Join(os.Args[1:], " ")
-	fmt.Println("Indexing all pages")
-	loadIndex()
-	fmt.Printf("Searching for %s\n", q)
-	for _, p := range search(q) {
-		t := strings.ReplaceAll(string(p.Html), "<b>", "\033[31;1m")
-		t = strings.ReplaceAll(t, "</b>", "\033[0m")
-		fmt.Printf("%s.md\n" + "\033[1;4m%s\033[0m (%d)\n" + "%s\n\n",
-			p.Name, p.Title, p.Score, t)
-	}
-}
-
 // getPort returns the environment variable ODDMU_PORT or the default
 // port, "8080".
 func getPort() string {
@@ -139,23 +159,17 @@ func getPort() string {
 	return port
 }
 
-func serve() {
+func main() {
 	http.HandleFunc("/", rootHandler)
 	http.HandleFunc("/view/", makeHandler(viewHandler))
 	http.HandleFunc("/edit/", makeHandler(editHandler))
 	http.HandleFunc("/save/", makeHandler(saveHandler))
+	http.HandleFunc("/add/", makeHandler(addHandler))
+	http.HandleFunc("/append/", makeHandler(appendHandler))
 	http.HandleFunc("/search", searchHandler)
-	fmt.Println("Indexing all pages")
+	fmt.Print("Indexing all pages\n")
 	loadIndex()
 	port := getPort()
 	fmt.Printf("Serving a wiki on port %s\n", port)
 	http.ListenAndServe(":"+port, nil)
 }
-
-func main() {
-	if len(os.Args) > 1 {
-		searchCommand()
-	} else {
-		serve()
-	}
-}