#compdef man apropos whatis

# Notes:
# - Solaris is seemingly the only OS that doesn't allow the `man n page` syntax;
#   you must use `man -s n page`
# - We assume that Linux distributions are using either man-db or mandoc
# - @todo Would be nice to support completing the initial operand as a section
#   name (on non-Solaris systems)
# - @todo We don't support the man-db feature of 'sub-pages' — that is, treating
#   pairs of operands like `git diff` as `git-diff`
# - @todo Option exclusivity isn't super accurate
# - @todo Solaris man accepts a single hyphen as the first option to disable
#   paging (like AIX's -c); we don't support that
# - @todo Linux apropos/whatis take options; we don't complete them yet

_man() {
  local dirs expl mrd awk variant noinsert
  local -a context line state state_descr args modes
  local -aU sects _manpath
  local -A opt_args val_args sect_descs

  if [[ $service == man ]]; then
    # We'll treat all mandoc-based systems (Alpine, various Illumos distros,
    # etc.) as OpenBSD
    _pick_variant -r variant openbsd='-S subsection' $OSTYPE ---

    modes=(
      -f -K -k -l -R -w -W
      --apropos
      --global-apropos
      --local-file
      --location
      --location-cat
      --recode
      --whatis
      --where
      --where-cat
    )
    [[ $variant == darwin* ]] && modes+=( -t )

    args=(
      "(${(j< >)modes})"{-f,--whatis}'[display short description (like whatis)]'
      "(${(j< >)modes})"{-k,--apropos}'[search for keyword (like apropos)]'
      '(-M --manpath)'{-M+,--manpath=}'[specify manual search path]:manual search path:_sequence -s\: _directories'
    )
    if [[ $variant == (darwin|dragonfly|freebsd|linux)* ]]; then
      args+=(
        '(-a -S -s --all --sections)'{-a,--all}'[display all matching pages]'
        '(-P --pager)'{-P+,--pager=}'[specify output pager]:pager:_path_commands'
        # @todo Could enumerate these
        '(-p --preprocessor)'{-p+,--preprocessor=}'[specify roff preprocessor sequence]:preprocessor sequence'
      )
    else
      args+=( '(-s)-a[display all matching pages]' )
    fi
    [[ $variant == (aix|solaris)* ]] || args+=(
      '(-C --config-file)'{-C+,--config-file=}'[specify configuration file]:configuration file:_files'
      "(${(j< >)modes})"{-w,--path,--where}'[display file locations]'
    )
    [[ $variant == (aix|netbsd|openbsd)* ]] || args+=(
      # @todo FreeBSD allows this to be given multiple times
      '(-d --debug)'{-d,--debug}'[display debugging information]'
    )
    [[ $variant == (darwin|dragonfly|freebsd|linux|solaris|aix)* ]] && args+=(
      '(-7 -H -t --ascii --html --troff)'{-t,--troff}'[format man page using troff]'
    )
    [[ $variant == (darwin|linux)* ]] && args+=(
      "(${(j< >)modes})"{-K,--global-apropos}'[search for keyword in all pages]'
      '(-m --systems)'{-m+,--systems=}'[search manual of specified system]:operating system'
    )
    [[ $variant == (darwin|dragonfly|freebsd)* ]] && args+=(
      '(: -)-h[display help information]'
      '(-a)-S+[specify manual sections to search]: :->sects'
    )
    [[ $variant == (dragonfly|freebsd)* ]] && args+=(
      # @todo Could enumerate these
      '-m[search manual of specified architecture]:architecture'
      '-o[use non-localized man pages]'
    )
    [[ $variant == (netbsd|openbsd)* ]] && args+=(
      '-c[disable paging]'
      '-m[augment manual search path]:manual search path:_sequence -s\: _directories'
      '(-a)-s+[specify manual section to search]: :->sects'
    )
    [[ $variant == linux* ]] && args+=(
      '(: -)'{-\?,--help}'[display help information]'
      '(-7 -t -H -T -Z --ascii --html --troff --troff-device --ditroff)'{-7,--ascii}'[translate man pages for 7-bit terminal]'
      '(-D --default)'{-D,--default}'[reset man to default options]'
      # @todo Could enumerate these
      '(-E --encoding)'{-E+,--encoding=}'[specify output encoding]:encoding'
      '(-e --extension)'{-e+,--extension=}'[specify sub-extension]:sub-extension'
      '(-H --html)'{-H-,--html=-}'[produce HTML output for specified browser]::Web browser:_path_commands'
      '(-i -I --ignore-case --match-case)'{-i,--ignore-case}'[search case-insensitively]'
      '(-i -I --ignore-case --match-case)'{-I,--match-case}'[search case-sensitively]'
      '(-L --locale)'{-L+,--locale=}'[specify locale]:locale:_locales'
      "(${(j< >)modes})"{-l+,--local-file=}'[format and display specified file]:*:::manual file:_files'
      "!(${(j< >)modes})"{--location,--location-cat}
      '--names-only[match only page names (with --regex or --wildcard)]'
      '(--nh --no-hyphenation)'{--nh,--no-hyphenation}'[disable hyphenation]'
      '(--nj --no-justification)'{--nj,--no-justification}'[disable justification]'
      '--no-subpages[do not combine pairs of page names into single page name]'
      # @todo Could enumerate these
      "(${(j< >)modes})"{-R+,--recode=}'[output man page in specified encoding]:encoding'
      '(-r --prompt)'{-r+,--prompt=}'[specify prompt for less]:less prompt'
      '(-a --all --wildcard)--regex[treat page name as regular expression]'
      '(-a -S -s --all --sections)'{-S+,-s+,--sections=}'[specify manual sections to search]: :->sects'
      # @todo Could enumerate these
      '(-T -t --troff --troff-device)'{-T-,--troff-device=-}'[specify roff output device]::roff output device'
      '(-u --update)'{-u,--update}'[update database caches]'
      '(: -)--usage[display brief usage information]'
      '(: -)'{-V,--version}'[display version information]'
      "(${(j< >)modes})"{-W,--where-cat}'[display cat file locations]'
      '--warnings=[enable specified groff warnings]:groff warnings'
      '(-a --all --regex)--wildcard[treat page name as shell glob]'
      # @todo Could enumerate these
      '(-X --gxditview)'{-X-,--gxditview=-}'[display output in gxditview using specified DPI]::resolution (DPI) [75]'
      # @todo Post-process how?
      '(-t --troff -Z --ditroff)'{-Z,--ditroff}'[post-process output for chosen device]'
    )
    [[ $variant == darwin* ]] && args+=(
      # We use _files here because browsers are usually in /Applications, which
      # typically isn't in PATH
      '-B+[specify browser to use for HTML files]:Web browser:_files'
      '-c[reformat source man page]'
      # @todo -d should be exclusive with this above
      '(-d)-D[display man page along with debugging information]'
      '(-D -F --preformat)'{-F,--preformat}'[format man page only (do not display)]'
      '-H+[specify command to render HTML as text]:HTML pager:_path_commands'
      # --help and --version are undocumented but functional
      '(: -)--help[display help information]'
      # -s is also undocumented; it's provided for compatibility with Solaris
      '!(-S)-s+: :->sects'
      '(: -)'{-v,--version}'[display version information]'
      "(${(j< >)modes})-W[display file locations, one per line, with no other information]"
    )
    [[ $variant == netbsd* ]] && args+=(
      '-h[display only synopsis lines]'
      '(: -)-p[display manual search path]'
      '-S+[display only man pages with file names matching specified string]:search string'
    )
    [[ $variant == openbsd* ]] && args+=(
      "(${(j< >)modes})-l+[format and display specified file]:*:::manual file:_files"
      # @todo Could enumerate these
      '-S[search manual of specified architecture]:architecture'
    )
    [[ $variant == solaris* ]] && args+=(
      "(${(j< >)modes})-l[display file locations]"
      '-r[format man page only (do not display)]'
      '(-a)-s+[specify manual sections to search]: :->sects'
      # @todo Does this in fact want a file path?
      '-T+[format man page using specified macro package]:macro package:_files'
    )
    [[ $variant == aix* ]] && args+=(
      '-c[display man page using cat]'
      '-F[display only first matching entry]'
      '-m[only search paths specified by -M/MANPATH]'
      '-r[search remotely]'
    )

    # Strip (most) long options from non-Linux platforms
    if [[ $variant == darwin* ]]; then
      args=( ${(M)args:#((#s)|*\))(\*|)(-[^-]|--(help|path|pref|vers))*} )
    elif [[ $variant != linux* ]]; then
      args=( ${(M)args:#((#s)|*\))(\*|)-[^-]*} )
    fi
  fi

  _arguments -s -S : $args '*::: :->man' && return 0
  [[ -n $state ]] || return 1

  # Override man path
  [[ -n ${opt_args[-M]} ]] &&
  _manpath=( ${(s<:>)opt_args[-M]} )

  # Restore cached man path to avoid $(manpath) if we can
  if (( ! $#_manpath )); then
    if (( ! $+_manpath_cache )); then
      typeset -gHA _manpath_cache
    fi
    if [[ -z $_manpath_cache[$MANPATH] ]]; then
      local mp
      mp=( ${(s.:.)$({ command man -w || manpath } 2>/dev/null)} )
      [[ "$mp" == *:* ]] && mp=( ${(s.:.)mp} )
      if (( $#mp )); then
        _manpath_cache[$MANPATH]=${(j.:.)mp}
      elif (( $#manpath )); then
        _manpath_cache[$MANPATH]=$MANPATH
      fi
    fi
    _manpath=( ${(s.:.)_manpath_cache[$MANPATH]} )
  fi

  # Augment man path
  if [[ -n ${opt_args[-m]} ]]; then
    [[ $variant == (netbsd|openbsd)* ]] &&
    _manpath+=( ${(s<:>)opt_args[-m]} )
  elif [[ $variant == aix* ]]; then
    # _manpath declared -U so no need to test
    _manpath+=( /usr/share/man )
  fi

  (( $#_manpath )) ||
      _manpath=( /usr/man(-/) /(opt|usr)/(pkg|dt|share|X11R6|local)/(cat|)man(-/) )

  # `sman' is the SGML manual directory for Solaris 7.
  # 1M is system administrator commands on SVR4

  mrd=(${^_manpath/\%L/${LANG:-En_US.ASCII}}/mandb(N))

  # $sect is from the command line, the "3p" in "man 3p memcpy".
  #   It may also be a |-joined (and later in the code "()"-enclosed) list of
  #   section names.
  #   TODO: disentangle this to always be an array.
  # $sect_dirname is from the filesystem, the "3" in "/usr/share/man/man3"
  # These are used by _man_pages
  local sect sect_dirname

  # Take care: We can't use the sections from these options until we've finished
  # completing them; otherwise (e.g.) -s1:<TAB> will give no results
  if
    [[ $service != man ]] || [[ $state == sects ]] || (( $+opt_args[-a] ))
  then
    sect='*'
  elif
    [[ $variant == (darwin|linux)* ]] &&
    [[ -n ${opt_args[(i)-S|-s|--sections]} ]]
  then
    noinsert=1
    sect=${opt_args[${opt_args[(i)-S|-s|--sections]}]//[:,]/|}
  elif
    [[ $variant == (netbsd|openbsd|solaris)* ]] && (( $+opt_args[-s] ))
  then
    noinsert=1
    sect=${opt_args[-s]//,/|}
  elif [[ $variant == (dragonfly|freebsd)* ]] && (( $+opt_args[-S] )); then
    noinsert=1
    sect=${opt_args[-S]//:/|}
  # It's only a small help, but, per man-db, we can avoid treating an initial
  # operand like `8139too` as a section name by ensuring that only the first
  # character is a digit. This doesn't do much for stuff like `2to3`, but we can
  # at least special-case a few common patterns for now
  elif
    (( CURRENT > 1 )) &&
    [[ $variant != solaris* ]] &&
    [[ ${${(Q)words[1]}##(2to3|7z)*} == ([0-9](|[^0-9[:punct:]]*)|[lnopx]) ]]
  then
    noinsert=1
    sect=$words[1]
  elif [[ -n ${sect:=$MANSECT} ]]; then
    sect=${sect//:/|}
  fi

  # Colons may have been escaped
  sect=${(Q)sect}

  if [[ $sect = (<->*|[lnopx]) || $sect = *\|* ]]; then
    sects=( ${(s.|.)sect} )

    # Most man implementations support partial matching of a page's
    # (sub-)section name — e.g., `3per` for `3perl`. The (sub-)section name may
    # or may not correspond to the directory name (most systems combine
    # sub-sections), but we'll assume that if it starts with a number and we're
    # not on Solaris (which doesn't support this feature at all) that we can do
    # a match against the leading number. This is irritating if you DO want the
    # exact sub-section specified, but unfortunately there's no way to determine
    # this programmatically — i guess we could add a style to control it
    () {
      for 1; do
        if [[ $OSTYPE == solaris* || $1 != <->* ]]; then
          dirs+=( $^_manpath/(sman|man|cat)$1(|.*)/ )
        else
          dirs+=( $^_manpath/(sman|man|cat)${1%%[^0-9]#}*/ )
        fi
      done
    } $sects

    sect=${(j<|>)sects}
    [[ $sect == *'|'* ]] && sect="($sect)"
    awk="\$2 == \"$sect\" {print \$1}"
  else
    sect=
    dirs=( $^_manpath/(sman|man|cat)*/ )
    awk='{print $1}'
  fi

  # Ignore directories with no pages inside
  dirs=( ${^dirs}(#qFN) )

  # Solaris 11 and on have a man-index directory that doesn't contain manpages
  dirs=( ${dirs:#*/man-index/} )
  sects=( ${(o)${${dirs##*(man|cat)}%.*}%/} )

  # If we've got this far, we can build our look-up table for descriptions of
  # the more common sections. Unless otherwise labelled, the more specific ones
  # come from Solaris or one of its variants
  (( $#sects )) && () {
    sect_descs=(
      0        'library headers'
      1        'general commands'
      1cups    'CUPS commands'
      1m       'maintenance commands'
      1openssl 'OpenSSL commands'
      2        'system calls'
      3        'library functions'
      3c       'C library functions'
      3curses  'curses library functions'
      3elf     'ELF library functions'
      3f       'Fortran library functions'
      3lua     'Lua features' # NetBSD
      3mail    'mailbox library functions'
      3openssl 'OpenSSL library functions'
      3pam     'PAM library functions'
      3pool    'pool configuration library functions'
      3proc    'process control library functions'
      3x11     'Xlib functions'
      3xcurses 'curses library functions [X/Open]'
      4        'devices and drivers'
      5        'file formats and conventions'
      3openssl 'OpenSSL configuration files'
      6        'games'
      7        'miscellanea'
      8        'maintenance commands and procedures'
      9        'kernel features'
      9lua     'Lua kernel bindings' # NetBSD
      l        'local documentation' # AIX, etc. — TCL on some systems?
      n        'new documentation' # AIX, etc.
      o        'old documentation' # AIX, etc.
      p        'public documentation' # AIX, etc.
      x        'X11 features'
    )

    # Add POSIX variants
    for 1 in ${(k)sect_descs}; do
      [[ $1 == <-> ]] || continue
      sect_descs+=( "${1}p" "${sect_descs[$1]} [POSIX]" )
    done

    # Add OS-specific stuff that's too risky for or overrides the general list
    [[ $OSTYPE == darwin*  ]] && sect_descs+=( n 'Tcl/Tk features' )
    [[ $OSTYPE == openbsd* ]] && sect_descs+=( 3p 'Perl features' )
    # @todo Oracle Solaris 11.4 adopts the BSD/Linux structure, making many of
    # these inaccurate — this should be handled accordingly in the future. If
    # OSTYPE isn't helpful (since other Solaris descendants may not follow
    # suit), we could perhaps use the presence of SysV-style sections under
    # _manpath as the determinant
    [[ $OSTYPE == solaris* ]] && sect_descs+=(
      1t  'Tcl/Tk features'
      3m  'mathematical library functions'
      4   'file formats and conventions'
      5   'miscellanea'
      7   'special files'
      7d  'devices'
      7fs 'file systems'
      7i  'ioctl requests'
      7m  'STREAMS modules'
      7p  'protocols'
      9e  'driver entry points'
      9f  'driver functions'
      9p  'driver properties'
      9s  'driver data structures'
    )
  }

  [[ $state == sects ]] && {
    local s
    local -a specs

    (( $#sects )) || {
      _message -e sections 'manual section'
      return 1
    }

    # Build specs from descriptions
    for s in $sects; do
      specs+=( "${s}:${(b)sect_descs[$s]}" )
    done
    specs=( ${specs%:} )

    if [[ $variant == (darwin|dragonfly|freebsd|linux)* ]]; then
      _sequence -s : _describe -t sections 'manual section' specs
    elif [[ $variant == solaris* ]]; then
      _sequence -s , _describe -t sections 'manual section' specs
    else
      _describe -t sections 'manual section' specs
    fi
    return
  }

  if zstyle -t ":completion:${curcontext}:manuals" separate-sections; then
    local d ret=1

    (( $#sects )) || return 1

    if [[ $PREFIX$SUFFIX == */* ]]; then
      _tags manuals.${^sects} files
    else
      _tags manuals.${^sects}
    fi

    while _tags; do
      for sect_dirname in $sects; do
        d=$sect_dirname
        (( $+sect_descs[$d] )) && d+=" (${sect_descs[$d]})"

        _requested manuals.$sect_dirname expl "manual page, section $d" _man_pages &&
            ret=0
      done
      [[ $PREFIX$SUFFIX == */* ]] &&
      _requested files expl directory _files -/ && ret=0
      (( ret )) || return 0
    done
    ## To fall back to other sections' manpages when completing filenames, like
    ## the 'else' codepath does:
    #
    # if (( ret )) && [[ $PREFIX$SUFFIX == */* ]]; then
    #   sect_dirname=
    #   _wanted manuals expl 'manual page' _man_pages && return
    # fi

    return 1
  else
    sect_dirname=
    _wanted manuals expl 'manual page' _man_pages
  fi
}

_man_pages() {
  local pages sopt tmp

  # What files corresponding to manual pages can end in.
  local suf='.((?|<->*|ntcl)(|.gz|.bz2|.z|.Z|.lzma))'

  if [[ $PREFIX$SUFFIX = */* ]]; then
    # Easy way to test for versions of man that allow file names.
    # This can't be a normal man page reference.
    # Try to complete by glob first.
    if [[ -n $sect_dirname ]]; then
      _path_files -g "*.*$sect_dirname*(|.gz|.bz2|.z|.Z|.lzma)" "$expl[@]"
    else
      _path_files -g "*$suf" "$expl[@]" && return
      _path_files "$expl[@]"
    fi
    return $?
  fi

  pages=( ${(M)dirs:#*$sect_dirname/} )
  pages=( ${^pages}/"*${sect:+.$sect"*"}" )
  pages=( ${^~pages}(N:t) )

  (($#mrd)) && pages[$#pages+1]=($(awk $awk $mrd))

  # Remove any compression suffix, then remove the minimum possible string
  # beginning with .<->: that handles problem cases like files called
  # `POSIX.1.5'.

  [[ $variant = solaris* ]] && sopt='-s '
  if ! ((CURRENT > 1 || noinsert)); then
    zstyle -s ":completion:${curcontext}:manuals.$sect_dirname" insert-sections tmp
  fi
  case "$tmp" in
    prepend|true|on|yes|1)
      compadd "$@" -P "$sopt$sect_dirname " - ${pages%$~suf}
    ;;
    suffix)
      compadd "$@" -s ".$sect_dirname" - ${pages%$~suf}
    ;;
    *)
      compadd "$@" - ${pages%$~suf}
    ;;
  esac
}

_man "$@"