From 9517f62de216b661c56bed0945c7d5c5277524f1 Mon Sep 17 00:00:00 2001
From: cblgh <cblgh@cblgh.org>
Date: Tue, 22 Nov 2022 14:08:44 +0100
Subject: [PATCH] tweak wording and minor details relating to preview queries

---
 crawler/crawler.go |  4 ++--
 docs/files.md      | 24 +++++++++++-------------
 util/util.go       |  2 ++
 3 files changed, 15 insertions(+), 15 deletions(-)

diff --git a/crawler/crawler.go b/crawler/crawler.go
index 7cb960e..e979b32 100644
--- a/crawler/crawler.go
+++ b/crawler/crawler.go
@@ -41,9 +41,9 @@ func getAboutHeuristics(path string) []string {
 func getPreviewQueries(path string) []string {
 	previewQueries := util.ReadList(path, "\n")
 	if len(previewQueries) > 0 {
-		return previewQueries;
+		return previewQueries
 	} else {
-		return []string{"main p", "article p", "section p", "p"};
+		return []string{"main p", "article p", "section p", "p"}
 	}
 }
 
diff --git a/docs/files.md b/docs/files.md
index c3db40a..1ae530a 100644
--- a/docs/files.md
+++ b/docs/files.md
@@ -123,21 +123,19 @@ are stopped from entering the search index. The default wordlist consists of the
 interesting concepts and verbs—such as `reading` and `books`, for example.
 
 #### `previewQueryList`
-A list of css selectors (one per line) to fetch preview paragraphs,
-the first paragraph found that passes a check against the `heuristics` file makes
-it into the search index. For each selector lieu tries the first four paragraphs
-found with each selector before skipping to the next one.
+A list of css selectors—one per line—used to fetch preview paragraphs. The first paragraph
+found passing a check against the `heuristics` file makes it into the search index. For
+each selector in `previewQueryList`, Lieu tries the first four paragraphs—as found by the
+selector—before trying to find a new set of paragraphs using the file's next selector.
 
-To get good results one usually wants to tune this to getting the first "real" paragraph
-after the header, or a summary paragraph if provided. It is also worth trying to avoind getting
-irelevant paragraphs as they clutter up your index and results, lieu will fall back to other
-preview sources.
+To get good results, one usually wants to tune this list to getting the first "real" paragraph
+after common page headers, or finding a summary paragraph. The default has been, at the time of
+writing, tuned for use with the [Fediring](https://fediring.net).
 
-The default has been (at the time of writing) tuned for use with the Fediring.
-
-Depending on how well the websites you are indexing are with semantic HTML this will
-get you the 70 to 90% solution. For the rest use heuristics and contact the creators of the
-websites you are tring to index, they (usually) appreciate the feedback.
+Depending on the structure of the websites you are indexing, this will get you 70-90% of the
+way in terms of accurate link descriptions. For the rest of the way, fine-tune `heuristics.txt`
+and reach out the creators of the websites you are indexing; they often appreciate the
+feedback.
 
 #### OpenSearch metadata
 If you are running your own instance of Lieu, you might want to look into changing the URL
diff --git a/util/util.go b/util/util.go
index 263871d..fab86a8 100644
--- a/util/util.go
+++ b/util/util.go
@@ -196,6 +196,8 @@ bannedSuffixes = "data/banned-suffixes.txt"
 boringWords = "data/boring-words.txt"
 # domains that won't be output as outgoing links
 boringDomains = "data/boring-domains.txt"
+# queries to search for finding preview text
+previewQueryList = "data/preview-query-list.txt"
 `)
 	err := ioutil.WriteFile("lieu.toml", conf, 0644)
 	Check(err)