3 files changed, 135 insertions(+), 1 deletions(-)

M bopher-ng.sh
M tools/README-tools.md
A tools/gmi2map.sh

@@ 15,6 15,8 @@
 # - ability to force-download pages instead of viewing regardless of their type
 # - displaying type 8 entries (as per RFC1436) as the telnet:// URI scheme
 
+shopt -s extglob # enable extended pattern matching (just to be sure)
+
 # save the command line parameters
 
 START_HOST="$1"

@@ 44,7 44,7 @@ This tool processes every line of text from the standard input to fit exactly th
 
 As `phlow.sh` does not know anything about hyphenation rules and doesn't do any heuristics, it just breaks at whatever whitespace is the closest to the page's right edge.
 
-Example - fitting the previous paragraph into 30-character width and prepend every line with 5 spaces (CR characters in the output are not shown):
+Example - fitting the previous paragraph into 30-character width and prepending every line with 5 spaces (CR characters in the output are not shown):
 ```
 $ echo 'This tool processes every line of text from the standard input to fit exactly the given amount of characters, optionally adding some leading and/or trailing whitespaces **after** the reflow is done. It also replaces all LF line endings with CRLF in the output to achieve maximum compatibility with legacy clients.' | bash phlow.sh 30 5
      This tool processes every     


@@ 62,4 62,43 @@ $ echo 'This tool processes every line of text from the standard input to fit ex
      legacy clients.               
 ```
 
+## `gmi2map.sh`
 
+This tool converts Gemtext documents into browsable Gophermaps. It basically combines the functionality of both previous tools and adds link processing and triple-backtick removal (because in Gopherspace, all text is supposed to be preformatted) on top of them. Unlike `gopherinfo.sh` though, it doesn't care about the maximum length of the source (if you need to, the reflow logic is there), but it **is** expecting the entire document from the standard input, and as such, **does** add the trailing dot at the end of the generated Gophermap. That's why, for the beginners, this sole script might actually be everything you need to get you started with Gopher publishing.
+
+Note that by default, reflow logic in `gmi2map.sh` is optional and you have to specify the page width yourself if you need it. Actually, full usage syntax looks like this:
+```
+cat [file] | gmi2map.sh [page_width] [leading_spaces] [trailing_spaces] [placeholder_char]
+```
+
+I.e. it looks like the `phlow.sh` and `gopherinfo.sh` options combined, but the spaces part only applies to the reflow, which is also off by default.
+
+Example - imagine we have this rudimentary Gemtext document in the `example.gmi` file:
+```
+I write short Gemtext here.
+
+I write a bit longer Gemtext here to showcase reflow capabilities of Bopher Tools' gmi2map.sh script, because it really is cool.
+
+=> gopher://happynetbox.com:79/1luxferre Anyway, why not publish it on Gopher?
+=> https://chronovir.us Or read my blog on Web...
+
+See ya!
+```
+
+When running `cat example.gmi | bash gmi2map.sh 67`, this file translates to the following Gophermap:
+
+```
+$ cat example.gmi | bash gmi2map.sh 67
+iI write short Gemtext here.                                            ;       ;       0
+i                                                                       ;       ;       0
+iI write a bit longer Gemtext here to showcase reflow capabilities      ;       ;       0
+iof Bopher Tools' gmi2map.sh script, because it really is cool.         ;       ;       0
+i                                                                       ;       ;       0
+1Anyway, why not publish it on Gopher?  luxferre        happynetbox.com 79
+hOr read my blog on Web...      URL:https://chronovir.us        ;       0
+i                                                                       ;       ;       0
+iSee ya!                                                                ;       ;       0
+.
+```
+
+Note that this tool hasn't been tested for all possible edge cases yet, so I recommend to always verify the generated maps yourself. But it definitely makes their creation a lot easier than doing it by hand.

@@ 0,0 1,93 @@
+#!/bin/bash
+# A simple helper tool to create a valid Gophermap from the Gemtext passed via standard input
+#
+# Usage: cat [file] | gmi2map.sh [page_width] [leading_spaces] [trailing_spaces] [placeholder_char]
+# (pass 0 as the reflow width if you want to pass the other parameters but don't want to turn on reflow logic)
+#
+# Created by Luxferre in 2023, released into public domain
+
+shopt -s extglob # enable extended pattern matching (just to be sure)
+
+TARGET_WIDTH="$1"
+LSPACES="$2"
+TSPACES="$3"
+DELIM="$4"
+
+TAB=$'\t'
+SPC=$'\x20'
+CRLF=$'\r\n'
+
+[[ -z "$TARGET_WIDTH" ]] && TARGET_WIDTH=0 # reflow off by default
+[[ -z "$LSPACES" ]] && LSPACES=0
+[[ -z "$TSPACES" ]] && TSPACES=0
+[[ -z "$DELIM" ]] && DELIM=';'
+
+# format strings to use in different situations:
+reflowfmt="%-$(( LSPACES ))s%-${TARGET_WIDTH}s%-$(( TSPACES ))s\n" # params: smth, line, smth
+infofmt="i%s${TAB}%s${TAB}%s${TAB}0${CRLF}"        # params: line, DELIM, DELIM
+gopherlinkfmt="%s%s${TAB}%s${TAB}%s${TAB}%d${CRLF}" # params: type, name, selector, host, port
+extlinkfmt="h%s${TAB}URL:%s${TAB}%s${TAB}0${CRLF}" # params: name, URL, DELIM
+
+reflow_line() { # single-line logic from phlow.sh, adapted into a function and separating by LF only
+  local line="$1"
+  local llen="${#line}" # get effective line length
+  if (( 0 == TARGET_WIDTH || llen < TARGET_WIDTH )); then # no need to run the logic for smaller lines or if TARGET_WIDTH is 0
+    printf "$reflowfmt" '' "$line" ''
+    return
+  fi
+  local lastws=0 # variable to track last whitespace
+  local cpos=0 # variable to track current position within the page line
+  local pagepos=0 # variable to track the position of new line start
+  local outbuf='' # temporary output buffer
+  local c='' # temporary character buffer
+  for ((i=0;i<llen;i++,cpos++)); do # start iterating over characters
+    c="${line:i:1}" # get the current one
+    if (( cpos >= TARGET_WIDTH )); then # we already exceeded the page width
+      (( lastws == 0 )) && lastws=$TARGET_WIDTH # no whitespace encountered here
+      printf "$reflowfmt" '' "${outbuf:0:$lastws}" '' # truncate the buffer
+      outbuf=''
+      pagepos=$(( pagepos + lastws ))
+      cpos=0
+      lastws=0
+      i=$pagepos # update current iteration index from the last valid whitespace
+    else # save the whitespace position if found
+      [[ "$c" == "$SPC" ]] && lastws="$cpos"
+      outbuf="${outbuf}${c}" # save the character itself
+    fi
+  done
+  [[ ! -z "$outbuf" ]] && printf "$reflowfmt" '' "$outbuf" '' # output the last unprocessed chunk
+}
+
+readarray -t LINES -d $'\n' # read the input line array (split by LF)
+for line in "${LINES[@]}"; do # iterate over the read text
+  line="${line%%$'\r'}" # remove a trailing CR if it is there
+  if [[ "${line:0:2}" == $'=>' ]]; then # we have a linkable resource
+    linkline="${line##=>*([[:blank:]])}" # remove the link signature and any leading whitespace
+    linkurl="${linkline%%[[:blank:]]*}" # treat anything until the next whitespace (or the end of line) as a URL
+    linkdesc="${linkline##${linkurl}*([[:blank:]])}" # remove the URL and any other leading whitespace to get the description
+    linkdesc="${linkdesc%%*([[:blank:]])}" # remove any trailing whitespace from the description
+    if [[ "$linkurl" =~ ^gopher:// ]]; then # now, proceed according to the URL type (just like in Bopher-NG)
+      preurl="${linkurl#gopher://}" # remove the scheme to ease parsing
+      hostport="${preurl%%/*}" # extract the host+:port part (where :port is also optional)
+      selpath="${preurl##$hostport}" # extract the selector+path part
+      reshost="${hostport%%:*}" # extract the hostname
+      resport="${hostport:(( 1 + ${#reshost} ))}" # extract the port
+      restype="${selpath:1:1}" # extract the type character
+      ressel="${selpath:2}" # extract the selector
+      [[ -z "$resport" ]] && resport=70 # default port is 70
+      [[ -z "$ressel" ]] && ressel="/" # default selector is root
+      [[ -z "$restype" ]] && restype=1 # default request type is a Gophermap
+      printf "$gopherlinkfmt" "$restype" "$linkdesc" "$ressel" "$reshost" "$resport"
+    else
+      printf "$extlinkfmt" "$linkdesc" "$linkurl" "$DELIM"
+    fi
+  else # we have an info line
+    infoline='' 
+    [[ "${line:0:3}" != $'```' ]] && infoline="$line" # ignore the preformatting togglers, pass everything else
+    readarray -t reflowed_lines -d $'\n' < <(reflow_line "$infoline")
+    for rline in "${reflowed_lines[@]}"; do # iterate over the reflowed line parts
+      printf "$infofmt" "$rline" "$DELIM" "$DELIM"
+    done
+  fi
+done
+printf '.\r\n' # finish the Gophermap generation