feat: Implement type 2 parser

samples/type2/df.1

@@ -0,0 +1,120 @@
+.\" DO NOT MODIFY THIS FILE!  It was generated by help2man 1.47.3.
+.TH DF "1" "February 2022" "GNU coreutils 8.32" "User Commands"
+.SH NAME
+df \- report file system disk space usage
+.SH SYNOPSIS
+.B df
+[\fI\,OPTION\/\fR]... [\fI\,FILE\/\fR]...
+.SH DESCRIPTION
+This manual page
+documents the GNU version of
+.BR df .
+.B df
+displays the amount of disk space available on the file system
+containing each file name argument.  If no file name is given, the
+space available on all currently mounted file systems is shown.  Disk
+space is shown in 1K blocks by default, unless the environment
+variable POSIXLY_CORRECT is set, in which case 512-byte blocks are
+used.
+.PP
+If an argument is the absolute file name of a disk device node containing a
+mounted file system,
+.B df
+shows the space available on that file system rather than on the
+file system containing the device node.  This version of
+.B df
+cannot show the space available on unmounted file systems, because on
+most kinds of systems doing so requires very nonportable intimate
+knowledge of file system structures.
+.SH OPTIONS
+.PP
+Show information about the file system on which each FILE resides,
+or all file systems by default.
+.PP
+Mandatory arguments to long options are mandatory for short options too.
+.TP
+\fB\-a\fR, \fB\-\-all\fR
+include pseudo, duplicate, inaccessible file systems
+.TP
+\fB\-B\fR, \fB\-\-block\-size\fR=\fI\,SIZE\/\fR
+scale sizes by SIZE before printing them; e.g.,
+\&'\-BM' prints sizes in units of 1,048,576 bytes;
+see SIZE format below
+.TP
+\fB\-h\fR, \fB\-\-human\-readable\fR
+print sizes in powers of 1024 (e.g., 1023M)
+.TP
+\fB\-H\fR, \fB\-\-si\fR
+print sizes in powers of 1000 (e.g., 1.1G)
+.TP
+\fB\-i\fR, \fB\-\-inodes\fR
+list inode information instead of block usage
+.TP
+\fB\-k\fR
+like \fB\-\-block\-size\fR=\fI\,1K\/\fR
+.TP
+\fB\-l\fR, \fB\-\-local\fR
+limit listing to local file systems
+.TP
+\fB\-\-no\-sync\fR
+do not invoke sync before getting usage info (default)
+.TP
+\fB\-\-output\fR[=\fI\,FIELD_LIST\/\fR]
+use the output format defined by FIELD_LIST,
+or print all fields if FIELD_LIST is omitted.
+.TP
+\fB\-P\fR, \fB\-\-portability\fR
+use the POSIX output format
+.TP
+\fB\-\-sync\fR
+invoke sync before getting usage info
+.TP
+\fB\-\-total\fR
+elide all entries insignificant to available space,
+and produce a grand total
+.TP
+\fB\-t\fR, \fB\-\-type\fR=\fI\,TYPE\/\fR
+limit listing to file systems of type TYPE
+.TP
+\fB\-T\fR, \fB\-\-print\-type\fR
+print file system type
+.TP
+\fB\-x\fR, \fB\-\-exclude\-type\fR=\fI\,TYPE\/\fR
+limit listing to file systems not of type TYPE
+.TP
+\fB\-v\fR
+(ignored)
+.TP
+\fB\-\-help\fR
+display this help and exit
+.TP
+\fB\-\-version\fR
+output version information and exit
+.PP
+Display values are in units of the first available SIZE from \fB\-\-block\-size\fR,
+and the DF_BLOCK_SIZE, BLOCK_SIZE and BLOCKSIZE environment variables.
+Otherwise, units default to 1024 bytes (or 512 if POSIXLY_CORRECT is set).
+.PP
+The SIZE argument is an integer and optional unit (example: 10K is 10*1024).
+Units are K,M,G,T,P,E,Z,Y (powers of 1024) or KB,MB,... (powers of 1000).
+Binary prefixes can be used, too: KiB=K, MiB=M, and so on.
+.PP
+FIELD_LIST is a comma\-separated list of columns to be included.  Valid
+field names are: 'source', 'fstype', 'itotal', 'iused', 'iavail', 'ipcent',
+\&'size', 'used', 'avail', 'pcent', 'file' and 'target' (see info page).
+.SH AUTHOR
+Written by Torbjorn Granlund, David MacKenzie, and Paul Eggert.
+.SH "REPORTING BUGS"
+GNU coreutils online help: <https://www.gnu.org/software/coreutils/>
+.br
+Report any translation bugs to <https://translationproject.org/team/>
+.SH COPYRIGHT
+Copyright \(co 2020 Free Software Foundation, Inc.
+License GPLv3+: GNU GPL version 3 or later <https://gnu.org/licenses/gpl.html>.
+.br
+This is free software: you are free to change and redistribute it.
+There is NO WARRANTY, to the extent permitted by law.
+.SH "SEE ALSO"
+Full documentation <https://www.gnu.org/software/coreutils/df>
+.br
+or available locally via: info \(aq(coreutils) df invocation\(aq

samples/type2/rfcomm.1

@@ -0,0 +1,128 @@
+.\" Man page generated from reStructuredText.
+.
+.
+.nr rst2man-indent-level 0
+.
+.de1 rstReportMargin
+\\$1 \\n[an-margin]
+level \\n[rst2man-indent-level]
+level margin: \\n[rst2man-indent\\n[rst2man-indent-level]]
+-
+\\n[rst2man-indent0]
+\\n[rst2man-indent1]
+\\n[rst2man-indent2]
+..
+.de1 INDENT
+.\" .rstReportMargin pre:
+. RS \\$1
+. nr rst2man-indent\\n[rst2man-indent-level] \\n[an-margin]
+. nr rst2man-indent-level +1
+.\" .rstReportMargin post:
+..
+.de UNINDENT
+. RE
+.\" indent \\n[an-margin]
+.\" old: \\n[rst2man-indent\\n[rst2man-indent-level]]
+.nr rst2man-indent-level -1
+.\" new: \\n[rst2man-indent\\n[rst2man-indent-level]]
+.in \\n[rst2man-indent\\n[rst2man-indent-level]]u
+..
+.TH "RFCOMM" 1 "April 28, 2002" "BlueZ" "Linux System Administration"
+.SH NAME
+rfcomm \- RFCOMM configuration utility
+.SH SYNOPSIS
+.sp
+\fBrfcomm\fP [\fIOPTIONS\fP] <\fICOMMAND\fP> <\fIdev\fP>
+.SH DESCRIPTION
+.sp
+\fBrfcomm(1)\fP is used to set up, maintain, and inspect the RFCOMM configuration
+of the Bluetooth subsystem in the Linux kernel. If no \fBcommand\fP is given,
+or if the option \fB\-a\fP is used, \fBrfcomm\fP prints information about the
+configured RFCOMM devices.
+.SH OPTIONS
+.INDENT 0.0
+.TP
+.B  \-h
+Gives a list of possible commands.
+.TP
+.B  \-a
+Prints information about all configured RFCOMM devices.
+.TP
+.B  \-r
+Switch TTY into raw mode (doesn\(aqt work with "bind").
+.UNINDENT
+.INDENT 0.0
+.TP
+.B \-i <\fIhciX\fP> | <\fIbdaddr\fP>
+The command is applied to device \fIhciX\fP, which must be the name or the
+address of an installed Bluetooth device. If not specified, the command
+will be use the first available Bluetooth device.
+.UNINDENT
+.INDENT 0.0
+.TP
+.B  \-A
+Enable authentication
+.TP
+.B  \-E
+Enable encryption
+.TP
+.B  \-S
+Secure connection
+.TP
+.B  \-C
+Become the central of a piconet
+.TP
+.BI \-L \ <seconds>
+Set linger timeout
+.UNINDENT
+.SH COMMANDS
+.INDENT 0.0
+.TP
+.B show <\fIdev\fP>
+Display the information about the specified device.
+.TP
+.B connect <\fIdev\fP> [\fIbdaddr\fP] [\fIchannel\fP]
+Connect the RFCOMM device to the remote Bluetooth device on the specified
+channel. If no  channel  is  specified, it will use the channel
+number \fB1\fP\&. This command can be terminated with the key sequence CTRL\-C.
+.TP
+.B listen <\fIdev\fP> [\fIchannel\fP] [\fIcmd\fP]
+Listen  on  a specified RFCOMM channel for incoming connections.  If no
+channel is specified, it will use the channel number \fB1\fP, but a channel
+must be specified before cmd. If cmd is given, it will be executed as soon
+as a  client  connects.  When the child process terminates or the client
+disconnect, the command will terminate. Occurrences of {} in cmd will be
+replaced by the name of the device used by the connection. This command
+can be terminated with the key sequence CTRL\-C.
+.TP
+.B watch <\fIdev\fP> [\fIchannel\fP] [\fIcmd\fP]
+Watch is identical to listen except that when the child process
+terminates or the client disconnect, the command will restart listening
+with the same parameters.
+.TP
+.B bind <\fIdev\fP> [\fIbdaddr\fP] [\fIchannel\fP]
+This binds the RFCOMM device to a remote Bluetooth device. The command
+does not establish a connection to the remote  device, it only creates
+the binding. The connection will be established right after an application
+tries to open the RFCOMM device. If no channel number is specified, it
+uses the channel number \fB1\fP\&.
+.TP
+.B release <\fIdev\fP>
+This command releases a defined RFCOMM binding.
+.sp
+If \fBall\fP is specified for the RFCOMM device, then all bindings will be
+removed.
+.UNINDENT
+.SH RESOURCES
+.sp
+\fI\%http://www.bluez.org\fP
+.SH REPORTING BUGS
+.sp
+\fI\%linux\-bluetooth@vger.kernel.org\fP
+.SH AUTHOR
+Marcel Holtmann <marcel@holtmann.org>
+.SH COPYRIGHT
+Free use of this software is granted under ther terms of the GNU
+Lesser General Public Licenses (LGPL).
+.\" Generated by docutils manpage writer.
+.

src/parse/mod.rs

@@ -1,4 +1,5 @@
 mod type1;
+mod type2;
 pub(super) mod util;
 
 use anyhow::{anyhow, Result};
@@ -34,7 +35,8 @@ where
 }
 
 pub fn parse_manpage_text<S: AsRef<str>>(cmd_name: &str, text: S) -> Option<Vec<Arg>> {
-  type1::parse(cmd_name, text.as_ref())
+  let text = text.as_ref();
+  type1::parse(cmd_name, text).or_else(|| type2::parse(cmd_name, text))
 }
 
 pub struct ManParseConfig {
@@ -241,7 +243,7 @@ fn filter_pages(
       if include {
         debug!("Found man page for {} at {}", cmd, path.display());
       }
-      if include && exclude {
+      if exclude && include_commands.is_some() {
         warn!("Command was both explicitly included and excluded: {}", cmd);
       }
 

src/parse/type1.rs

@@ -1,5 +1,4 @@
 use log::debug;
-use regex::Regex;
 
 use super::{util, Arg};
 
@@ -13,16 +12,23 @@ pub fn parse(cmd_name: &str, page_text: &str) -> Option<Vec<Arg>> {
       let content = captures.get(1).unwrap().as_str();
       let mut args = Vec::new();
 
-      for para in content.split(".PP") {
+      let mut paras = content.split(".PP");
+      paras.next(); // Discard the part before the first option
+      for para in paras {
         if let Some(end) = para.find(".RE") {
           let data = &para[0..end];
           let data = util::remove_groff_formatting(data);
           let mut data = data.split(".RS 4");
           let options = data.next().unwrap();
           let desc = data.next();
-          if let Some(arg) = make_arg(options, desc) {
+          if let Some(arg) = util::make_arg(options, desc) {
             args.push(arg);
           }
+        } else {
+          debug!(
+            "No .RE found to end description, para: {}",
+            util::truncate(&para, 40)
+          );
         }
       }
 
@@ -31,62 +37,3 @@ pub fn parse(cmd_name: &str, page_text: &str) -> Option<Vec<Arg>> {
     None => None,
   }
 }
-
-/// Parse the line of options after .PP and the description after it
-///
-/// Ported from Fish's `built_command`
-fn make_arg(options: &str, desc: Option<&str>) -> Option<Arg> {
-  // Unquote the options string
-  let options = options.trim();
-  let options = if options.len() < 2 {
-    options
-  } else if options.starts_with('"') && options.ends_with('"') {
-    &options[1..options.len() - 1]
-  } else if options.starts_with('\'') && options.ends_with('\'') {
-    &options[1..options.len() - 1]
-  } else {
-    options
-  };
-
-  let mut forms = Vec::new();
-  let delim = Regex::new(r#"[ ,="|]"#).unwrap();
-  for option in delim.split(options) {
-    let option = Regex::new(r"\[.*\]").unwrap().replace(option, "");
-    // todo Fish doesn't replace <.*> so maybe this is wrong
-    let option = Regex::new(r"<.*>").unwrap().replace(&option, "");
-    // todo this is ridiculously verbose
-    let option =
-      option.trim_matches(" \t\r\n[](){}.:!".chars().collect::<Vec<_>>().as_slice());
-    if !option.starts_with('-') || option == "-" || option == "--" {
-      continue;
-    }
-    if Regex::new(r"\{\}\(\)").unwrap().is_match(option) {
-      continue;
-    }
-    forms.push(option.to_owned());
-  }
-
-  if forms.is_empty() {
-    let desc = if let Some(desc) = desc {
-      &desc.trim()[..40]
-    } else {
-      ""
-    };
-    debug!("No options found in '{}', desc: '{}'", options.trim(), desc);
-    return None;
-  }
-
-  match desc {
-    Some(desc) => {
-      let desc = desc.trim().replace("\n", " ");
-      let desc = desc.trim_end_matches('.');
-      // Remove bogus escapes
-      let desc = desc.replace(r"\'", "").replace(r"\.", "");
-
-      let desc = util::trim_desc(desc);
-      let desc = if desc.is_empty() { None } else { Some(desc) };
-      Some(Arg { forms, desc })
-    }
-    None => Some(Arg { forms, desc: None }),
-  }
-}